Audio-visual fine-tuning of audio-only ASR models
원문 초록
Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL) approaches have been developed to reduce this dependence on transcribed AV data, but these methods are quite complex and computationally expensive. In this work, we propose replacing these expensive AV-SSL methods with a simple and fast \textit{audio-only} SSL method, and then performing AV supervised fine-tuning. We show that this approach is competitive with state-of-the-art (SOTA) AV-SSL methods on the LRS3-TED benchmark task (within 0.5% absolute WER), while being dramatically simpler and more efficient (12-30x faster to pre-train). Furthermore, we show we can extend this approach to convert a SOTA audio-only ASR model into an AV model. By doing so, we match SOTA AV-SSL results, even though no AV data was used during pre-training.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GigaAM: Efficient Self-Supervised Learner for Speech Recognition
MSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
토론
이 논문과 연결된 포럼 글이 아직 없습니다.