Speaker diarization, the process of identifying "who spoke when" in audio recordings, is essential for understanding classroom dynamics. However, classroom settings present distinct challenges, including poor recording quality, high levels of background noise, overlapping speech, and the difficulty of accurately capturing children's voices. This study investigates the effectiveness of multi-stage diarization models using Nvidia's NeMo diarization pipeline. We assess the impact of denoising on diarization accuracy and compare various voice activity detection (VAD) models, including self-supervised transformer-based frame-wise VAD models. We also explore a hybrid VAD approach that integrates Automatic Speech Recognition (ASR) word-level timestamps with frame-level VAD predictions. We conduct experiments using two datasets from English speaking classrooms to separate teacher vs. student speech and to separate all speakers. Our results show that denoising significantly improves the Diarization Error Rate (DER) by reducing the rate of missed speech. Additionally, training on both denoised and noisy datasets leads to substantial performance gains in noisy conditions. The hybrid VAD model leads to further improvements in speech detection, achieving a DER as low as 17% in teacher-student experiments and 45% in all-speaker experiments. However, we also identified trade-offs between voice activity detection and speaker confusion. Overall, our study highlights the effectiveness of multi-stage diarization models and integrating ASR-based information for enhancing speaker diarization in noisy classroom environments.
The integration of Environmental, Social, and Governance (ESG) factors into corporate decision-making is a fundamental aspect of sustainable finance. However, ensuring that business practices align with evolving regulatory frameworks remains a persistent challenge. AI-driven solutions for automatically assessing the alignment of sustainability reports and non-financial disclosures with specific ESG activities could greatly support this process. Yet, this task remains complex due to the limitations of general-purpose Large Language Models (LLMs) in domain-specific contexts and the scarcity of structured, high-quality datasets. In this paper, we investigate the ability of current-generation LLMs to identify text related to environmental activities. Furthermore, we demonstrate that their performance can be significantly enhanced through fine-tuning on a combination of original and synthetically generated data. To this end, we introduce ESG-Activities, a benchmark dataset containing 1,325 labelled text segments classified according to the EU ESG taxonomy. Our experimental results show that fine-tuning on ESG-Activities significantly enhances classification accuracy, with open models such as Llama 7B and Gemma 7B outperforming large proprietary solutions in specific configurations. These findings have important implications for financial analysts, policymakers, and AI researchers seeking to enhance ESG transparency and compliance through advanced natural language processing techniques.
Voice data is increasingly being used in modern digital communications, yet there is still a lack of comprehensive tools for automated voice analysis and characterization. To this end, we developed the VANPY (Voice Analysis in Python) framework for automated pre-processing, feature extraction, and classification of voice data. The VANPY is an open-source end-to-end comprehensive framework that was developed for the purpose of speaker characterization from voice data. The framework is designed with extensibility in mind, allowing for easy integration of new components and adaptation to various voice analysis applications. It currently incorporates over fifteen voice analysis components - including music/speech separation, voice activity detection, speaker embedding, vocal feature extraction, and various classification models. Four of the VANPY's components were developed in-house and integrated into the framework to extend its speaker characterization capabilities: gender classification, emotion classification, age regression, and height regression. The models demonstrate robust performance across various datasets, although not surpassing state-of-the-art performance. As a proof of concept, we demonstrate the framework's ability to extract speaker characteristics on a use-case challenge of analyzing character voices from the movie "Pulp Fiction." The results illustrate the framework's capability to extract multiple speaker characteristics, including gender, age, height, emotion type, and emotion intensity measured across three dimensions: arousal, dominance, and valence.
Purpose: Surgical performance depends not only on surgeons' technical skills but also on team communication within and across the different professional groups present during the operation. Therefore, automatically identifying team communication in the OR is crucial for patient safety and advances in the development of computer-assisted surgical workflow analysis and intra-operative support systems. To take the first step, we propose a new task of detecting communication briefings involving all OR team members, i.e. the team Time-out and the StOP?-protocol, by localizing their start and end times in video recordings of surgical operations. Methods: We generate an OR dataset of real surgeries, called Team-OR, with more than one hundred hours of surgical videos captured by the multi-view camera system in the OR. The dataset contains temporal annotations of 33 Time-out and 22 StOP?-protocol activities in total. We then propose a novel group activity detection approach, where we encode both scene context and action features, and use an efficient neural network model to output the results. Results: The experimental results on the Team-OR dataset show that our approach outperforms existing state-of-the-art temporal action detection approaches. It also demonstrates the lack of research on group activities in the OR, proving the significance of our dataset. Conclusion: We investigate the Team Time-Out and the StOP?-protocol in the OR, by presenting the first OR dataset with temporal annotations of group activities protocols, and introducing a novel group activity detection approach that outperforms existing approaches. Code is available at https://github.com/CAMMA-public/Team-OR.
The spatial diversity and multiplexing advantages of massive multi-input-multi-output (mMIMO) can significantly improve the capacity of massive non-orthogonal multiple access (NOMA) in machine type communications. However, state-of-the-art grant-free massive NOMA schemes for mMIMO systems require accurate estimation of random access channels to perform activity detection and the following coherent data demodulation, which suffers from excessive pilot overhead and access latency. To address this, we propose a pre-equalization aided grant-free massive access scheme for mMIMO systems, where an iterative detection scheme is conceived. Specifically, the base station (BS) firstly activates one of its antennas (i.e., beacon antenna) to broadcast a beacon signal, which facilitates the user equipment (UEs) to perform downlink channel estimation and pre-equalize the uplink random access signal with respect to the channels associated with the beacon antenna. During the uplink transmission stage, the BS detects UEs' activity and data by using the proposed iterative detection algorithm, which consists of three modules: coarse data detection (DD), data-aided channel estimation (CE), and fine DD. In the proposed algorithm, the joint activity and DD is firstly performed based on the signals received by the beacon antenna. Subsequently, the DD is further refined by iteratively performing data-aided CE module and fine DD module using signals received by all BS antennas. Our simulation results demonstrate that the proposed scheme outperforms state-of-the-art mMIMO-based grant-free massive NOMA schemes with the same access latency. Simulation codes are provided to reproduce the results in this article: https://github.com/owenwang517/tvt-2025.
Neovascular age-related macular degeneration (nAMD) is a leading cause of vision loss among older adults, where disease activity detection and progression prediction are critical for nAMD management in terms of timely drug administration and improving patient outcomes. Recent advancements in deep learning offer a promising solution for predicting changes in AMD from optical coherence tomography (OCT) retinal volumes. In this work, we proposed deep learning models for the two tasks of the public MARIO Challenge at MICCAI 2024, designed to detect and forecast changes in nAMD severity with longitudinal retinal OCT. For the first task, we employ a Vision Transformer (ViT) based Siamese Network to detect changes in AMD severity by comparing scan embeddings of a patient from different time points. To train a model to forecast the change after 3 months, we exploit, for the first time, an Earth Mover (Wasserstein) Distance-based loss to harness the ordinal relation within the severity change classes. Both models ranked high on the preliminary leaderboard, demonstrating that their predictive capabilities could facilitate nAMD treatment management.
We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders. The Temporal Signal Semantic Encoder splits feature learning into high and low-frequency components, using a novel Signed Mask-Attention mechanism to emphasize important areas and downplay unimportant ones, with the features fused using ContraNorm. The Local Sensitive Response Encoder captures fluctuations without learning. These feature pyramids are then combined using a new cross-attention fusion mechanism. We also introduce a dataset with over 2,114 activity segments across 553 WiFi CSI samples, each lasting around 85 seconds. Extensive experiments show our method outperforms challenging baselines.
This work introduces the first framework for reconstructing surgical dialogue from unstructured real-world recordings, which is crucial for characterizing teaching tasks. In surgical training, the formative verbal feedback that trainers provide to trainees during live surgeries is crucial for ensuring safety, correcting behavior immediately, and facilitating long-term skill acquisition. However, analyzing and quantifying this feedback is challenging due to its unstructured and specialized nature. Automated systems are essential to manage these complexities at scale, allowing for the creation of structured datasets that enhance feedback analysis and improve surgical education. Our framework integrates voice activity detection, speaker diarization, and automated speech recaognition, with a novel enhancement that 1) removes hallucinations (non-existent utterances generated during speech recognition fueled by noise in the operating room) and 2) separates speech from trainers and trainees using few-shot voice samples. These aspects are vital for reconstructing accurate surgical dialogues and understanding the roles of operating room participants. Using data from 33 real-world surgeries, we demonstrated the system's capability to reconstruct surgical teaching dialogues and detect feedback instances effectively (F1 score of 0.79+/-0.07). Moreover, our hallucination removal step improves feedback detection performance by ~14%. Evaluation on downstream clinically relevant tasks of predicting Behavioral Adjustment of trainees and classifying Technical feedback, showed performances comparable to manual annotations with F1 scores of 0.82+/0.03 and 0.81+/0.03 respectively. These results highlight the effectiveness of our framework in supporting clinically relevant tasks and improving over manual methods.
To facilitate natural and intuitive interactions with diverse user groups in real-world settings, social robots must be capable of addressing the varying requirements and expectations of these groups while adapting their behavior based on user feedback. While previous research often focuses on specific demographics, we present a novel framework for adaptive Human-Robot Interaction (HRI) that tailors interactions to different user groups and enables individual users to modulate interactions through both minor and major interruptions. Our primary contributions include the development of an adaptive, ROS-based HRI framework with an open-source code base. This framework supports natural interactions through advanced speech recognition and voice activity detection, and leverages a large language model (LLM) as a dialogue bridge. We validate the efficiency of our framework through module tests and system trials, demonstrating its high accuracy in age recognition and its robustness to repeated user inputs and plan changes.
We introduce Moshi, a speech-text foundation model and full-duplex spoken dialogue framework. Current systems for spoken dialogue rely on pipelines of independent components, namely voice activity detection, speech recognition, textual dialogue and text-to-speech. Such frameworks cannot emulate the experience of real conversations. First, their complexity induces a latency of several seconds between interactions. Second, text being the intermediate modality for dialogue, non-linguistic information that modifies meaning -- such as emotion or non-speech sounds -- is lost in the interaction. Finally, they rely on a segmentation into speaker turns, which does not take into account overlapping speech, interruptions and interjections. Moshi solves these independent issues altogether by casting spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. We moreover extend the hierarchical semantic-to-acoustic token generation of previous work to first predict time-aligned text tokens as a prefix to audio tokens. Not only this "Inner Monologue" method significantly improves the linguistic quality of generated speech, but we also illustrate how it can provide streaming speech recognition and text-to-speech. Our resulting model is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice, and is available at https://github.com/kyutai-labs/moshi.
InaGVAD is an audio corpus collected from 10 French radio and 18 TV channels categorized into 4 groups: generalist radio, music radio, news TV, and generalist TV. It contains 277 1-minute-long annotated recordings aimed at representing the acoustic diversity of French audiovisual programs and was primarily designed to build systems able to monitor men's and women's speaking time in media. inaGVAD is provided with Voice Activity Detection (VAD) and Speaker Gender Segmentation (SGS) annotations extended with overlap, speaker traits (gender, age, voice quality), and 10 non-speech event categories. Annotation distributions are detailed for each channel category. This dataset is partitioned into a 1h development and a 3h37 test subset, allowing fair and reproducible system evaluation. A benchmark of 6 freely available VAD software is presented, showing diverse abilities based on channel and non-speech event categories. Two existing SGS systems are evaluated on the corpus and compared against a baseline X-vector transfer learning strategy, trained on the development subset. Results demonstrate that our proposal, trained on a single - but diverse - hour of data, achieved competitive SGS results. The entire inaGVAD package; including corpus, annotations, evaluation scripts, and baseline training code; is made freely accessible, fostering future advancement in the domain.
Overlapped speech is notoriously problematic for speaker diarization systems. Consequently, the use of speech separation has recently been proposed to improve their performance. Although promising, speech separation models struggle with realistic data because they are trained on simulated mixtures with a fixed number of speakers. In this work, we introduce a new speech separation-guided diarization scheme suitable for the online speaker diarization of long meeting recordings with a variable number of speakers, as present in the AMI corpus. We envisage ConvTasNet and DPRNN as alternatives for the separation networks, with two or three output sources. To obtain the speaker diarization result, voice activity detection is applied on each estimated source. The final model is fine-tuned end-to-end, after first adapting the separation to real data using AMI. The system operates on short segments, and inference is performed by stitching the local predictions using speaker embeddings and incremental clustering. The results show that our system improves the state-of-the-art on the AMI headset mix, using no oracle information and under full evaluation (no collar and including overlapped speech). Finally, we show the strength of our system particularly on overlapped speech sections.
Activity detection is an important task in the next generation grant-free multiple access. While there are a number of existing algorithms designed for this purpose, they mostly require precise information about the network, such as large-scale fading coefficients, small-scale fading channel statistics, noise variance at the access points, and user activity probability. Acquiring these information would take a significant overhead and their estimated values might not be accurate. This problem is even more severe in cell-free networks as there are many of these parameters to be acquired. Therefore, this paper sets out to investigate the activity detection problem without the above-mentioned information. In order to handle so many unknown parameters, this paper employs the Bayesian approach, where the unknown variables are endowed with prior distributions which effectively act as regularizations. Together with the likelihood function, a maximum a posteriori (MAP) estimator and a variational inference algorithm are derived. Extensive simulations demonstrate that the proposed methods, even without the knowledge of these system parameters, perform better than existing state-of-the-art methods, such as covariance-based and approximate message passing methods.
Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavailable for dialogue systems. This paper proposes integrating AER with automatic speech recognition (ASR) and speaker diarisation (SD) in a jointly-trained system. Distinct output layers are built for four sub-tasks including AER, ASR, voice activity detection and speaker classification based on a shared encoder. Taking the audio of a conversation as input, the integrated system finds all speech segments and transcribes the corresponding emotion classes, word sequences, and speaker identities. Two metrics are proposed to evaluate AER performance with automatic segmentation based on time-weighted emotion and speaker classification errors. Results on the IEMOCAP dataset show that the proposed system consistently outperforms two baselines with separately trained single-task systems on AER, ASR and SD.
We introduce "ivrit.ai", a comprehensive Hebrew speech dataset, addressing the distinct lack of extensive, high-quality resources for advancing Automated Speech Recognition (ASR) technology in Hebrew. With over 3,300 speech hours and a over a thousand diverse speakers, ivrit.ai offers a substantial compilation of Hebrew speech across various contexts. It is delivered in three forms to cater to varying research needs: raw unprocessed audio; data post-Voice Activity Detection, and partially transcribed data. The dataset stands out for its legal accessibility, permitting use at no cost, thereby serving as a crucial resource for researchers, developers, and commercial entities. ivrit.ai opens up numerous applications, offering vast potential to enhance AI capabilities in Hebrew. Future efforts aim to expand ivrit.ai further, thereby advancing Hebrew's standing in AI research and technology.
The analysis of conversations recorded in everyday life requires privacy protection. In this contribution, we explore a privacy-preserving feature extraction method based on input feature dimension reduction, spectral smoothing and the low-cost speaker anonymization technique based on McAdams coefficient. We assess the utility of the feature extraction methods with a voice activity detection and a speaker diarization system, while privacy protection is determined with a speech recognition and a speaker verification model. We show that the combination of McAdams coefficient and spectral smoothing maintains the utility while improving privacy.
This paper introduces FunASR, an open-source speech recognition toolkit designed to bridge the gap between academic research and industrial applications. FunASR offers models trained on large-scale industrial corpora and the ability to deploy them in applications. The toolkit's flagship model, Paraformer, is a non-autoregressive end-to-end speech recognition model that has been trained on a manually annotated Mandarin speech recognition dataset that contains 60,000 hours of speech. To improve the performance of Paraformer, we have added timestamp prediction and hotword customization capabilities to the standard Paraformer backbone. In addition, to facilitate model deployment, we have open-sourced a voice activity detection model based on the Feedforward Sequential Memory Network (FSMN-VAD) and a text post-processing punctuation model based on the controllable time-delay Transformer (CT-Transformer), both of which were trained on industrial corpora. These functional modules provide a solid foundation for building high-precision long audio speech recognition services. Compared to other models trained on open datasets, Paraformer demonstrates superior performance.
Noise reduction is a crucial aspect of hearing aids, which researchers have been striving to address over the years. However, most existing noise reduction algorithms have primarily been evaluated using English. Considering the linguistic differences between English and Sinhala languages, including variation in syllable structures and vowel duration, it is very important to assess the performance of noise reduction tailored to the Sinhala language. This paper presents a comprehensive analysis between wavelet transformation and adaptive filters for noise reduction in Sinhala languages. We investigate the performance of ten wavelet families with soft and hard thresholding methods against adaptive filters with Normalized Least Mean Square, Least Mean Square Average Normalized Least Mean Square, Recursive Least Square, and Adaptive Filtering Averaging optimization algorithms along with cepstral and energy-based voice activity detection algorithms. The performance evaluation is done using objective metrics; Signal to Noise Ratio (SNR) and Perceptual Evaluation of Speech Quality (PESQ) and a subjective metric; Mean Opinion Score (MOS). A newly recorded Sinhala language audio dataset and the NOIZEUS database by the University of Texas, Dallas were used for the evaluation. Our code is available at https://github.com/ChathukiKet/Evaluation-of-Noise-Reduction-Methods
Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly. It builds upon the target-speaker voice activity detection (TS-VAD) diarization approach, which assumes that initial speaker embeddings are available. We replace the final combined speaker activity estimation network of TS-VAD with a network that produces speaker activity estimates at a time-frequency resolution. Those act as masks for source extraction, either via masking or via beamforming. The technique can be applied both for single-channel and multi-channel input and, in both cases, achieves a new state-of-the-art word error rate (WER) on the LibriCSS meeting data recognition task. We further compute speaker-aware and speaker-agnostic WERs to isolate the contribution of diarization errors to the overall WER performance.
We propose Token Turing Machines (TTM), a sequential, autoregressive Transformer model with memory for real-world sequential visual understanding. Our model is inspired by the seminal Neural Turing Machine, and has an external memory consisting of a set of tokens which summarise the previous history (i.e., frames). This memory is efficiently addressed, read and written using a Transformer as the processing unit/controller at each step. The model's memory module ensures that a new observation will only be processed with the contents of the memory (and not the entire history), meaning that it can efficiently process long sequences with a bounded computational cost at each step. We show that TTM outperforms other alternatives, such as other Transformer models designed for long sequences and recurrent neural networks, on two real-world sequential visual understanding tasks: online temporal activity detection from videos and vision-based robot action policy learning. Code is publicly available at: https://github.com/google-research/scenic/tree/main/scenic/projects/token_turing