paper-with-me

Papers

Multi-Channel Transformer Transducer for Speech Recognition

2021-08-30 · Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris, Maurizio Omologo

Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end ASR for improved accuracy. However, this approach is characterized by a high computational complexity, which prevents it from being deployed in on-device systems. In this paper, we present a novel speech recognition model, Multi-Channel Transformer Transducer (MCTT), which features end-to-end multi-channel training, low computation cost, and low latency so that it is suitable for streaming decoding in on-device speech recognition. In a far-field in-house dataset, our MCTT outperforms stagewise multi-channel models with transformer-transducer up to 6.01% relative WER improvement (WERR). In addition, MCTT outperforms the multi-channel transformer up to 11.62% WERR, and is 15.8 times faster in terms of inference speed. We further show that we can improve the computational cost of MCTT by constraining the future and previous context in attention computations.

📄 PDF Abstract BibTeX arXiv:2108.12953

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Research on Modeling Units of Transformer Transducer for Mandarin Speech Recognition

2020-04-26 · Li Fu, Xiaoxiao Li, Libo Zi

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel …

speech-recognitionSpeech Recognition

Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks

2018-10-08 · Takuya Yoshioka, Hakan Erdogan, Zhuo Chen, Xiong Xiao 외

The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accu…

speech-recognitionSpeech RecognitionSpeech Separation

Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition

2020-11-02 · Jae-Jin Jeon, Eesung Kim

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural…

speech-recognitionSpeech Recognition

Transformer-Transducer: End-to-End Speech Recognition with Self-Attention

2019-10-28 · Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang 외

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and c…

speech-recognitionSpeech Recognition

Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset

2020-10-22 · Xie Chen, Yu Wu, Zhenghao Wang, Shujie Liu 외

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is …

Decoderspeech-recognitionSpeech Recognition