Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

• URL: http://arxiv.org/abs/2211.00786v1
• Date: Tue, 1 Nov 2022 23:43:15 GMT
• Title: Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
• Authors: Shaan Bijwadia, Shuo-yiin Chang, Bo Li, Tara Sainath, Chao Zhang, Yanzhang He
• Abstract summary: We propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) model. We introduce a "switch" connection, which trains the EP to consume either the audio frames directly or low-level latent representations from the ASR model. This results in a single E2E model that can be used during inference to perform frame filtering at low cost.
• Score: 17.160006765475988
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic speech recognition (ASR) systems typically rely on an external endpointer (EP) model to identify speech boundaries. In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask model, improving EP quality by optionally leveraging information from the ASR audio encoder. We introduce a "switch" connection, which trains the EP to consume either the audio frames directly or low-level latent representations from the ASR model. This results in a single E2E model that can be used during inference to perform frame filtering at low cost, and also make high quality end-of-query (EOQ) predictions based on ongoing ASR computation. We present results on a voice search test set showing that, compared to separate single-task models, this approach reduces median endpoint latency by 120 ms (30.8% reduction), and 90th percentile latency by 170 ms (23.0% reduction), without regressing word error rate. For continuous recognition, WER improves by 10.6% (relative).

Related papers

• Convoifilter: A case study of doing cocktail party speech recognition [59.80042864360884]
  The model can decrease ASR's word error rate (WER) from 80% to 26.4% through this approach. We openly share our pre-trained model to foster further research hf.co/nguyenvulebinh/voice-filter.
  arXiv  Detail & Related papers  (2023-08-22T12:09:30Z)
• Streaming Speech-to-Confusion Network Speech Recognition [19.720334657478475]
  We present a novel streaming ASR architecture that outputs a confusion network while maintaining limited latency. We show that 1-best results of our model are on par with a comparable RNN-T system. We also show that our model outperforms a strong RNN-T baseline on a far-field voice assistant task.
  arXiv  Detail & Related papers  (2023-06-02T20:28:14Z)
• Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings [53.11450530896623]
  This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize "who spoke what" Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion. The proposed model achieves substantially better accuracy than a prior streaming model and shows comparable or sometimes even superior results to the state-of-the-art offline SA-ASR model.
  arXiv  Detail & Related papers  (2022-03-30T21:42:00Z)
• Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition [45.858039215825656]
  We propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours.
  arXiv  Detail & Related papers  (2021-06-08T12:12:33Z)
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers [56.56220390953412]
  We extend our prior work by introducing the Conformer architecture to further improve the accuracy. We demonstrate that the extended Transformer provides state-of-the-art end-to-end ASR performance.
  arXiv  Detail & Related papers  (2021-04-19T16:18:00Z)
• WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition [59.975078145303605]
  We propose a novel framework, namely WNARS, using hybrid CTC-attention AED models and weighted finite-state transducers. On the AISHELL-1 task, our WNARS achieves a character error rate of 5.22% with 640ms latency, to the best of our knowledge, which is the state-of-the-art performance for online ASR.
  arXiv  Detail & Related papers  (2021-04-08T07:56:03Z)
• Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone [43.77139614544301]
  Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR) In this paper, we extensively investigate a two-step approach where we first pre-train a serialized output training (SOT)-based multi-talker ASR. With fine-tuning on the 70 hours of the AMI-SDM training data, our SOT ASR model achieves a word error rate (WER) of 21.2% for the AMI-SDM evaluation set.
  arXiv  Detail & Related papers  (2021-03-31T02:43:32Z)
• FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization [78.46088089185156]
  Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. Existing approaches penalize emission delay by manipulating per-token or per-frame probability prediction in sequence transducer models. We propose a sequence-level emission regularization method, named FastEmit, that applies latency regularization directly on per-sequence probability in training transducer models.
  arXiv  Detail & Related papers  (2020-10-21T17:05:01Z)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.