Global Normalization for Streaming Speech Recognition in a Modular Framework
We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact computation of the denominator for the sequence-level normalization. Through theoretical and empirical results, we demonstrate that by switching to a globally normalized model, the word error rate gap between streaming and non-streaming speech-recognition models can be greatly reduced (by more than 50\% on the Librispeech dataset). This model is developed in a modular framework which encompasses all the common neural speech recognition models. The modularity of this framework enables controlled comparison of modelling choices and creation of new models.
Code (1)
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation
End-to-end (E2E) automatic speech recognition (ASR) can operate in two modes: streaming and non-streaming, each with its pros and cons. Streaming ASR processes the speech frames in real-time as it is being received, whil…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderKnowledge Distillation+2Streaming, fast and accurate on-device Inverse Text Normalization for Automatic Speech Recognition
Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However, humans prefer a written form output. To bridge this gap, ASR systems usually employ Inverse Text Normalization (ITN). In previou…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+2Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
The demand for fast and accurate incremental speech recognition increases as the applications of automatic speech recognition (ASR) proliferate. Incremental speech recognizers output chunks of partially recognized words …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1Endpoint Detection for Streaming End-to-End Multi-talker ASR
Streaming end-to-end multi-talker speech recognition aims at transcribing the overlapped speech from conversations or meetings with an all-neural model in a streaming fashion, which is fundamentally different from a modu…
Sentencespeech-recognitionSpeech RecognitionSpeech SeparationDynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integra…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+3