Multi-turn RNN-T for streaming recognition of multi-party speech

• URL: http://arxiv.org/abs/2112.10200v1
• Date: Sun, 19 Dec 2021 17:22:58 GMT
• Title: Multi-turn RNN-T for streaming recognition of multi-party speech
• Authors: Ilya Sklyar, Anna Piunova, Xianrui Zheng, Yulan Liu
• Abstract summary: This work takes real-time applicability as the first priority in model design and addresses a few challenges in previous work on multi-speaker recurrent neural network transducer (MS-RNN-T) We introduce on-the-fly overlapping speech simulation during training, yielding 14% relative word error rate (WER) improvement on LibriSpeechMix test set. We propose a novel multi-turn RNN-T (MT-RNN-T) model with an overlap-based target arrangement strategy that generalizes to an arbitrary number of speakers without changes in the model architecture.
• Score: 2.899379040028688
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve superior recognition accuracy compared to modular systems. However, these models do not ensure real-time applicability due to their dependency on full audio context. This work takes real-time applicability as the first priority in model design and addresses a few challenges in previous work on multi-speaker recurrent neural network transducer (MS-RNN-T). First, we introduce on-the-fly overlapping speech simulation during training, yielding 14% relative word error rate (WER) improvement on LibriSpeechMix test set. Second, we propose a novel multi-turn RNN-T (MT-RNN-T) model with an overlap-based target arrangement strategy that generalizes to an arbitrary number of speakers without changes in the model architecture. We investigate the impact of the maximum number of speakers seen during training on MT-RNN-T performance on LibriCSS test set, and report 28% relative WER improvement over the two-speaker MS-RNN-T. Third, we experiment with a rich transcription strategy for joint recognition and segmentation of multi-party speech. Through an in-depth analysis, we discuss potential pitfalls of the proposed system as well as promising future research directions.

Related papers

• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding [60.292702363839716]
  Current SOTA backbone networks for speaker embedding are designed to aggregate multi-scale features from an utterance with multi-branch network architectures for speaker representation. We propose an effective temporal multi-scale (TMS) model where multi-scale branches could be efficiently designed in a speaker embedding network almost without increasing computational costs.
  arXiv  Detail & Related papers  (2022-03-17T05:49:35Z)
• MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances [94.70787497137854]
  We propose a multi-scale frequency-channel attention (MFA) to characterize speakers at different scales through a novel dual-path design which consists of a convolutional neural network and TDNN. We evaluate the proposed MFA on the VoxCeleb database and observe that the proposed framework with MFA can achieve state-of-the-art performance while reducing parameters and complexity.
  arXiv  Detail & Related papers  (2022-02-03T14:57:05Z)
• Streaming end-to-end multi-talker speech recognition [34.76106500736099]
  We propose the Streaming Unmixing and Recognition Transducer (SURT) for end-to-end multi-talker speech recognition. Our model employs the Recurrent Neural Network Transducer (RNN-T) as the backbone that can meet various latency constraints. Based on experiments on the publicly available LibriSpeechMix dataset, we show that HEAT can achieve better accuracy compared with PIT.
  arXiv  Detail & Related papers  (2020-11-26T06:28:04Z)
• Multi-task Language Modeling for Improving Speech Recognition of Rare Words [14.745696312889763]
  We propose a second-pass system with multi-task learning, utilizing semantic targets (such as intent and slot prediction) to improve speech recognition performance. Our best ASR system with multi-task LM shows 4.6% WERR deduction compared with RNN Transducer only ASR baseline for rare words recognition.
  arXiv  Detail & Related papers  (2020-11-23T20:40:44Z)
• Streaming Multi-speaker ASR with RNN-T [8.701566919381223]
  This work focuses on multi-speaker speech recognition based on a recurrent neural network transducer (RNN-T) We show that guiding separation with speaker order labels in the former case enhances the high-level speaker tracking capability of RNN-T. Our best model achieves a WER of 10.2% on simulated 2-speaker Libri data, which is competitive with the previously reported state-of-the-art nonstreaming model (10.3%)
  arXiv  Detail & Related papers  (2020-11-23T19:10:40Z)
• Many-to-Many Voice Transformer Network [55.17770019619078]
  This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework. It enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech.
  arXiv  Detail & Related papers  (2020-05-18T04:02:08Z)
• AutoSpeech: Neural Architecture Search for Speaker Recognition [108.69505815793028]
  We propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech. Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times. Results demonstrate that the derived CNN architectures significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.
  arXiv  Detail & Related papers  (2020-05-07T02:53:47Z)

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.