The aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data contain high discriminative speaker information, even more reliable than the acoustic ones. In this study we analyze how an appropriate fusion of both kind of features is able to obtain good results in these cases. The proposed system is based on an iterative algorithm where a LSTM network is used as a speaker classifier. The network is fed with character-level word embeddings and a GMM based acoustic score created with the output labels from previous iterations. The presented algorithm has been evaluated in a Call-Center database, which is composed of telephone interview audios. The combination of acoustic features and linguistic content shows a 84.29% improvement in terms of a word-level DER as compared to a HMM/VB baseline system. The results of this study confirms that linguistic content can be efficiently used for some speaker recognition tasks.
We present SPEAR, a continuous receiver-to-receiver acoustic neural warping field for spatial acoustic effects prediction in an acoustic 3D space with a single stationary audio source. Unlike traditional source-to-receiver modelling methods that require prior space acoustic properties knowledge to rigorously model audio propagation from source to receiver, we propose to predict by warping the spatial acoustic effects from one reference receiver position to another target receiver position, so that the warped audio essentially accommodates all spatial acoustic effects belonging to the target position. SPEAR can be trained in a data much more readily accessible manner, in which we simply ask two robots to independently record spatial audio at different positions. We further theoretically prove the universal existence of the warping field if and only if one audio source presents. Three physical principles are incorporated to guide SPEAR network design, leading to the learned warping field physically meaningful. We demonstrate SPEAR superiority on both synthetic, photo-realistic and real-world dataset, showing the huge potential of SPEAR to various down-stream robotic tasks.
Echolocation is the prime sensing modality for many species of bats, who show the intricate ability to perform a plethora of tasks in complex and unstructured environments. Understanding this exceptional feat of sensorimotor interaction is a key aspect into building more robust and performant man-made sonar sensors. In order to better understand the underlying perception mechanisms it is important to get a good insight into the nature of the reflected signals that the bat perceives. While ensonification experiments are in important way to better understand the nature of these signals, they are as time-consuming to perform as they are informative. In this paper we present SonoTraceLab, an open-source software package for simulating both technical as well as biological sonar systems in complex scenes. Using simulation approaches can drastically increase insights into the nature of biological echolocation systems, while reducing the time- and material complexity of performing them.
Producing synthetic voice, similar to human-like sound, is an emerging novelty of modern interactive media systems. Text-To-Speech (TTS) systems try to generate synthetic and authentic voices via text input. Besides, well known and familiar dubbing, announcing and narrating voices, as valuable possessions of any media organization, can be kept forever by utilizing TTS and Voice Conversion (VC) algorithms . The emergence of deep learning approaches has made such TTS systems more accurate and accessible. To understand TTS systems better, this paper investigates the key components of such systems including text analysis, acoustic modelling and vocoding. The paper then provides details of important state-of-the-art TTS systems based on deep learning. Finally, a comparison is made between recently released systems in term of backbone architecture, type of input and conversion, vocoder used and subjective assessment (MOS). Accordingly, Tacotron 2, Transformer TTS, WaveNet and FastSpeech 1 are among the most successful TTS systems ever released. In the discussion section, some suggestions are made to develop a TTS system with regard to the intended application.
We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching. Careful design choices additionally ensure each synthesis step is fast to run. The method is probabilistic, non-autoregressive, and learns to speak from scratch without external alignments. Compared to strong pre-trained baseline models, the Matcha-TTS system has the smallest memory footprint, rivals the speed of the fastest models on long utterances, and attains the highest mean opinion score in a listening test. Please see https://shivammehta25.github.io/Matcha-TTS/ for audio examples, code, and pre-trained models.
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptions, Normalizing Flows and Diffusion Probabilistic Models were recently proposed as alternatives. In this paper, we compare traditional L1/L2-based approaches to diffusion and flow-based approaches for the tasks of prosody and mel-spectrogram prediction for text-to-speech synthesis. We use a prosody model to generate log-f0 and duration features, which are used to condition an acoustic model that generates mel-spectrograms. Experimental results demonstrate that the flow-based model achieves the best performance for spectrogram prediction, improving over equivalent diffusion and L1 models. Meanwhile, both diffusion and flow-based prosody predictors result in significant improvements over a typical L2-trained prosody models.
One of the major challenges in acoustic modelling of child speech is the rapid changes that occur in the children's articulators as they grow up, their differing growth rates and the subsequent high variability in the same age group. These high acoustic variations along with the scarcity of child speech corpora have impeded the development of a reliable speech recognition system for children. In this paper, a speaker- and age-invariant training approach based on adversarial multi-task learning is proposed. The system consists of one generator shared network that learns to generate speaker- and age-invariant features connected to three discrimination networks, for phoneme, age, and speaker. The generator network is trained to minimize the phoneme-discrimination loss and maximize the speaker- and age-discrimination losses in an adversarial multi-task learning fashion. The generator network is a Time Delay Neural Network (TDNN) architecture while the three discriminators are feed-forward networks. The system was applied to the OGI speech corpora and achieved a 13% reduction in the WER of the ASR.
In Automatic Speech Recognition, GMM-HMM had been widely used for acoustic modelling. With the current advancement of deep learning, the Gaussian Mixture Model (GMM) from acoustic models has been replaced with Deep Neural Network, namely DNN-HMM Acoustic Models. The GMM models are widely used to create the alignments of the training data for the hybrid deep neural network model, thus making it an important task to create accurate alignments. Many factors such as training dataset size, training data augmentation, model hyperparameters, etc., affect the model learning. Traditionally in machine learning, larger datasets tend to have better performance, while smaller datasets tend to trigger over-fitting. The collection of speech data and their accurate transcriptions is a significant challenge that varies over different languages, and in most cases, it might be limited to big organizations. Moreover, in the case of available large datasets, training a model using such data requires additional time and computing resources, which may not be available. While the data about the accuracy of state-of-the-art ASR models on open-source datasets are published, the study about the impact of the size of a dataset on acoustic models is not readily available. This work aims to investigate the impact of dataset size variations on the performance of various GMM-HMM Acoustic Models and their respective computational costs.
The Mandarin Chinese language is known to be strongly influenced by a rich set of regional accents, while Mandarin speech with each accent is quite low resource. Hence, an important task in Mandarin speech recognition is to appropriately model the acoustic variabilities imposed by accents. In this paper, an investigation of implicit and explicit use of accent information on a range of deep neural network (DNN) based acoustic modelling techniques is conducted. Meanwhile, approaches of multi-accent modelling including multi-style training, multi-accent decision tree state tying, DNN tandem and multi-level adaptive network (MLAN) tandem hidden Markov model (HMM) modelling are combined and compared in this paper. On a low resource accented Mandarin speech recognition task consisting of four regional accents, an improved MLAN tandem HMM systems explicitly leveraging the accent information was proposed and significantly outperformed the baseline accent independent DNN tandem systems by 0.8%-1.5% absolute (6%-9% relative) in character error rate after sequence level discriminative training and adaptation.
Current state of the art acoustic models can easily comprise more than 100 million parameters. This growing complexity demands larger training datasets to maintain a decent generalization of the final decision function. An ideal dataset is not necessarily large in size, but large with respect to the amount of unique speakers, utilized hardware and varying recording conditions. This enables a machine learning model to explore as much of the domain-specific input space as possible during parameter estimation. This work introduces Common Phone, a gender-balanced, multilingual corpus recorded from more than 11.000 contributors via Mozilla's Common Voice project. It comprises around 116 hours of speech enriched with automatically generated phonetic segmentation. A Wav2Vec 2.0 acoustic model was trained with the Common Phone to perform phonetic symbol recognition and validate the quality of the generated phonetic annotation. The architecture achieved a PER of 18.1 % on the entire test set, computed with all 101 unique phonetic symbols, showing slight differences between the individual languages. We conclude that Common Phone provides sufficient variability and reliable phonetic annotation to help bridging the gap between research and application of acoustic models.
Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model: highly expressive voices are still challenging even to recent TTS architectures since there seems to be a trade-off between expressiveness in a generated audio and its signal quality. In this paper, we present a set of techniques that can be leveraged to enhance the signal quality of a highly-expressive voice without the use of additional data. The proposed techniques include: tuning the autoregressive loop's granularity during training; using Generative Adversarial Networks in acoustic modelling; and the use of Variational Auto-Encoders in both the acoustic model and the neural vocoder. We show that, when combined, these techniques greatly closed the gap in perceived naturalness between the baseline system and recordings by 39% in terms of MUSHRA scores for an expressive celebrity voice.
This paper describes the SPAPL system for the INTERSPEECH 2021 Challenge: Shared Task on Automatic Speech Recognition for Non-Native Children's Speech in German. ~ 5 hours of transcribed data and ~ 60 hours of untranscribed data are provided to develop a German ASR system for children. For the training of the transcribed data, we propose a non-speech state discriminative loss (NSDL) to mitigate the influence of long-duration non-speech segments within speech utterances. In order to explore the use of the untranscribed data, various approaches are implemented and combined together to incrementally improve the system performance. First, bidirectional autoregressive predictive coding (Bi-APC) is used to learn initial parameters for acoustic modelling using the provided untranscribed data. Second, incremental semi-supervised learning is further used to iteratively generate pseudo-transcribed data. Third, different data augmentation schemes are used at different training stages to increase the variability and size of the training data. Finally, a recurrent neural network language model (RNNLM) is used for rescoring. Our system achieves a word error rate (WER) of 39.68% on the evaluation data, an approximately 12% relative improvement over the official baseline (45.21%).
Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their body development, as well as the lack of available child speech data. Young readers speech additionally displays peculiarities, such as slow reading rate and presence of reading mistakes, that hardens the task. This work attempts to tackle the main challenges in phone acoustic modelling for young child speech with limited data, and improve understanding of strengths and weaknesses of a wide selection of model architectures in this domain. We find that transfer learning techniques are highly efficient on end-to-end architectures for adult-to-child adaptation with a small amount of child speech data. Through transfer learning, a Transformer model complemented with a Connectionist Temporal Classification (CTC) objective function, reaches a phone error rate of 28.1%, outperforming a state-of-the-art DNN-HMM model by 6.6% relative, as well as other end-to-end architectures by more than 8.5% relative. An analysis of the models' performance on two specific reading tasks (isolated words and sentences) is provided, showing the influence of the utterance length on attention-based and CTC-based models. The Transformer+CTC model displays an ability to better detect reading mistakes made by children, that can be attributed to the CTC objective function effectively constraining the attention mechanisms to be monotonic.
The two-dimensional (2D) numerical approaches for vocal tract (VT) modelling can afford a better balance between the low computational cost and accurate rendering of acoustic wave propagation. However, they require a high spatio-temporal resolution in the numerical scheme for a precise estimation of acoustic formants at the simulation run-time expense. We have recently proposed a new VT acoustic modelling technique, known as the 2.5D Finite-Difference Time-Domain (2.5D FDTD), which extends the existing 2D FDTD approach by adding tube depth to its acoustic wave solver. In this work, first, the simulated acoustic outputs of our new model are shown to be comparable with the 2D FDTD and a realistic 3D FEM VT model at a low spatio-temporal resolution. Next, a radiation model is developed by including a circular baffle around the VT as head geometry. The transfer functions of the radiation model are analyzed using five different vocal tract shapes for vowel sounds /a/, /e/, /i/, /o/ and /u/.
This work studies the use of deep neural networks (DNNs) to address automatic language identification (LID). Motivated by their recent success in acoustic modelling, we adapt DNNs to the problem of identifying the language of a given spoken utterance from short-term acoustic features. The proposed approach is compared to state-of-the-art i-vector based acoustic systems on two different datasets: Google 5M LID corpus and NIST LRE 2009. Results show how LID can largely benefit from using DNNs, especially when a large amount of training data is available. We found relative improvements up to 70%, in Cavg, over the baseline system.
We propose a method for zero-resource domain adaptation of DNN acoustic models, for use in low-resource situations where the only in-language training data available may be poorly matched to the intended target domain. Our method uses a multi-lingual model in which several DNN layers are shared between languages. This architecture enables domain adaptation transforms learned for one well-resourced language to be applied to an entirely different low-resource language. First, to develop the technique we use English as a well-resourced language and take Spanish to mimic a low-resource language. Experiments in domain adaptation between the conversational telephone speech (CTS) domain and broadcast news (BN) domain demonstrate a 29% relative WER improvement on Spanish BN test data by using only English adaptation data. Second, we demonstrate the effectiveness of the method for low-resource languages with a poor match to the well-resourced language. Even in this scenario, the proposed method achieves relative WER improvements of 18-27% by using solely English data for domain adaptation. Compared to other related approaches based on multi-task and multi-condition training, the proposed method is able to better exploit well-resource language data for improved acoustic modelling of the low-resource target domain.
Existing speech processing systems consist of different modules, individually optimized for a specific task such as acoustic modelling or feature extraction. In addition to not assuring optimality of the system, the disjoint nature of current speech processing systems make them unsuitable for ubiquitous health applications. We propose WaDeNet, an end-to-end model for mobile speech processing. In order to incorporate spectral features, WaDeNet embeds wavelet decomposition of the speech signal within the architecture. This allows WaDeNet to learn from spectral features in an end-to-end manner, thus alleviating the need for feature extraction and successive modules that are currently present in speech processing systems. WaDeNet outperforms the current state of the art in datasets that involve speech for mobile health applications such as non-invasive emotion recognition. WaDeNet achieves an average increase in accuracy of 6.36% when compared to the existing state of the art models. Additionally, WaDeNet is considerably lighter than a simple CNNs with a similar architecture.
In this work, we explore the benefits of using multilingual bottleneck features (mBNF) in acoustic modelling for the automatic speech recognition of code-switched (CS) speech in African languages. The unavailability of annotated corpora in the languages of interest has always been a primary challenge when developing speech recognition systems for this severely under-resourced type of speech. Hence, it is worthwhile to investigate the potential of using speech corpora available for other better-resourced languages to improve speech recognition performance. To achieve this, we train a mBNF extractor using nine Southern Bantu languages that form part of the freely available multilingual NCHLT corpus. We append these mBNFs to the existing MFCCs, pitch features and i-vectors to train acoustic models for automatic speech recognition (ASR) in the target code-switched languages. Our results show that the inclusion of the mBNF features leads to clear performance improvements over a baseline trained without the mBNFs for code-switched English-isiZulu, English-isiXhosa, English-Sesotho and English-Setswana speech.
We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for acoustic modelling, to separate the influence of pitch and timbre. This facilitates the modelling of the large variability of pitch in the singing voice. Our network takes a block of consecutive frame-wise linguistic and fundamental frequency features, along with global singer identity as input and outputs vocoder features, corresponding to the block of features. This block-wise approach, along with the training methodology allows us to model temporal dependencies within the features of the input block. For inference, sequential blocks are concatenated using an overlap-add procedure. We show that the performance of our model is competitive with regards to the state-of-the-art and the original sample using objective metrics and a subjective listening test. We also present examples of the synthesis on a supplementary website and the source code via GitHub.
This paper considers the impact of automatic segmentation on the fully-automatic, semi-supervised training of automatic speech recognition (ASR) systems for five-lingual code-switched (CS) speech. Four automatic segmentation techniques were evaluated in terms of the recognition performance of an ASR system trained on the resulting segments in a semi-supervised manner. The system's output was compared with the recognition rates achieved by a semi-supervised system trained on manually assigned segments. Three of the automatic techniques use a newly proposed convolutional neural network (CNN) model for framewise classification, and include a novel form of HMM smoothing of the CNN outputs. Automatic segmentation was applied in combination with automatic speaker diarization. The best-performing segmentation technique was also tested without speaker diarization. An evaluation based on 248 unsegmented soap opera episodes indicated that voice activity detection (VAD) based on a CNN followed by Gaussian mixture modelhidden Markov model smoothing (CNN-GMM-HMM) yields the best ASR performance. The semi-supervised system trained with the resulting segments achieved an overall WER improvement of 1.1% absolute over the system trained with manually created segments. Furthermore, we found that system performance improved even further when the automatic segmentation was used in conjunction with speaker diarization.