2023-03-21 更新
A Deep Learning System for Domain-specific speech Recognition
Authors:Yanan Jia
As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on domain-specific speech especially under low-resource settings. The author works with pre-trained DeepSpeech2 and Wav2Vec2 acoustic models to develop benefit-specific ASR systems. The domain-specific data are collected using proposed semi-supervised learning annotation with little human intervention. The best performance comes from a fine-tuned Wav2Vec2-Large-LV60 acoustic model with an external KenLM, which surpasses the Google and AWS ASR systems on benefit-specific speech. The viability of using error prone ASR transcriptions as part of spoken language understanding (SLU) is also investigated. Results of a benefit-specific natural language understanding (NLU) task show that the domain-specific fine-tuned ASR system can outperform the commercial ASR systems even when its transcriptions have higher word error rate (WER), and the results between fine-tuned ASR and human transcriptions are similar.
PDF 4th International Conference on Natural Language Processing and Computational Linguistics (NLPCL 2023)
点此查看论文截图
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition
Authors:Xiaoyu Yang, Qiujia Li, Chao Zhang, Philip C. Woodland
Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), knowledge distillation (KD) is often required in practice to transfer the knowledge learned by large teacher models into much smaller student models with affordable computation and memory costs. This paper proposes a novel two-stage KD framework to distil the knowledge from multiple speech foundation models as teachers into a single student neural transducer model for ASR. In the first stage, the student model encoder is pre-trained using the embeddings extracted from multiple teacher models. In the second stage, the student encoder is fine-tuned with the audio-text pairs based on the ASR task. Experiments on the LibriSpeech 100-hour subset show that the proposed KD framework improves the performance of both streaming and non-streaming student models when using only one teacher. The performance of the student model can be further enhanced when multiple teachers are used jointly, achieving word error rate reductions (WERRs) of 17.5% and 10.6%. Our proposed framework can be combined with other existing KD methods to achieve further improvements. Further WERRs were obtained by incorporating extra unlabelled data during encoder pre-training, leading to a total relative WERR of 55.0% on the non-streaming student model.
PDF
点此查看论文截图
On-the-fly Text Retrieval for End-to-End ASR Adaptation
Authors:Bolaji Yusuf, Aditya Gourav, Ankur Gandhe, Ivan Bulyko
End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore, since they store the entire corpus in their parameters, rare words can be challenging to recall. In this work, we propose augmenting a transducer-based ASR model with a retrieval language model, which directly retrieves from an external text corpus plausible completions for a partial ASR hypothesis. These completions are then integrated into subsequent predictions by an adapter, which is trained once, so that the corpus of interest can be switched without incurring the computational overhead of retraining. Our experiments show that the proposed model significantly improves the performance of a transducer baseline on a pair of question-answering datasets. Further, it outperforms shallow fusion on recognition of named entities by about 7 relative; when the two are combined, the relative improvement increases to 13%.
PDF Accepted to ICASSP 2023; Appendix added to include ablations that could not fit into the conference 4-page limit
点此查看论文截图
EmoTalk: Speech-driven emotional disentanglement for 3D face animation
Authors:Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan
Speech-driven 3D face animation aims to generate realistic facial expressions that match the speech content and emotion. However, existing methods often neglect emotional facial expressions or fail to disentangle them from speech content. To address this issue, this paper proposes an end-to-end neural network to disentangle different emotions in speech so as to generate rich 3D facial expressions. Specifically, we introduce the emotion disentangling encoder (EDE) to disentangle the emotion and content in the speech by cross-reconstructed speech signals with different emotion labels. Then an emotion-guided feature fusion decoder is employed to generate a 3D talking face with enhanced emotion. The decoder is driven by the disentangled identity, emotional, and content embeddings so as to generate controllable personal and emotional styles. Finally, considering the scarcity of the 3D emotional talking face data, we resort to the supervision of facial blendshapes, which enables the reconstruction of plausible 3D faces from 2D emotional data, and contribute a large-scale 3D emotional talking face dataset (3D-ETF) to train the network. Our experiments and user studies demonstrate that our approach outperforms state-of-the-art methods and exhibits more diverse facial movements. We recommend watching the supplementary video: https://ziqiaopeng.github.io/emotalk
PDF
点此查看论文截图
Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech
Authors:Maryam Fazel-Zarandi, Wei-Ning Hsu
Self-supervised learning leverages unlabeled data effectively, improving label efficiency and generalization to domains without labeled data. While recent work has studied generalization to more acoustic/linguistic domains, languages, and modalities, these investigations are limited to single-source speech with one primary speaker in the recording. This paper presents Cocktail HuBERT, a self-supervised learning framework that generalizes to mixture speech using a masked pseudo source separation objective. This objective encourages the model to identify the number of sources, separate and understand the context, and infer the content of masked regions represented as discovered units. Cocktail HuBERT outperforms state-of-the-art results with 69% lower WER on multi-speaker ASR, 31% lower DER on diarization, and is competitive on single- and multi-speaker tasks from SUPERB.
PDF ICASSP 2023
点此查看论文截图