paper-with-me

Papers

Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data

2023-05-25 · Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takanori Ashihara, Kohei Matsuura, Tomohiro Tanaka, Ryo Masumura, Atsunori Ogawa, Taichi Asami

Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra computation costs of a target speech extraction frontend, which is a critical barrier to quick response. TS-RNNT is trained end-to-end given the input speech (i.e., mixtures and enrollment speech) and reference transcriptions. The training mixtures are generally simulated by mixing single-talker signals, but conventional TS-RNNT training does not utilize single-speaker signals. This paper proposes using knowledge distillation (KD) to exploit the parallel mixture/single-talker speech data. Our proposed KD scheme uses an RNNT system pretrained with the target single-talker speech input to generate pseudo labels for the TS-RNNT training. Experimental results show that TS-RNNT systems trained with the proposed KD scheme outperform a baseline TS-RNNT.

📄 PDF Abstract BibTeX arXiv:2305.15971

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSpeech Extractionspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder

2022-11-02 · Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi, Shinji Watanabe

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modelling+2

Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models

2021-10-07 · Xiaoyu Yang, Qiujia Li, Philip C. Woodland

Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems. Since it is impractical to use large …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Knowledge DistillationLanguage Modelling+2

CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition

2021-06-14 · Rupak Vignesh Swaminathan, Brian King, Grant P. Strimel, Jasha Droppo 외

We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs naturally have a high entropy and conta…

DecoderKnowledge Distillationspeech-recognitionSpeech Recognition

Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation

2023-06-27 · Haitao Tang, Yu Fu, Lei Sun, Jiabin Xue 외

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effecti…

Knowledge Distillationspeech-recognitionSpeech Recognition

Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection

2021-09-23 · Wei Xia, Han Lu, Quan Wang, Anshuman Tripathi 외

In this paper, we present a novel speaker diarization system for streaming on-device applications. In this system, we use a transformer transducer to detect the speaker turns, represent each speaker turn by a speaker emb…

Clusteringspeaker-diarizationSpeaker Diarization