Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition
To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and word-end-based phoneme label augmentation is proposed to improve performance. Utilizing the local dependency of phonemes, we adopt a simplified neural network structure and a straightforward integration with the external word-level language model to preserve the consistency of seq-to-seq modeling. We also present a simple, stable and efficient training procedure using frame-wise cross-entropy loss. A phonetic context size of one is shown to be sufficient for the best performance. A simplified scheduled sampling approach is applied for further improvement and different decoding approaches are briefly compared. The overall performance of our best model is comparable to state-of-the-art (SOTA) results for the TED-LIUM Release 2 and Switchboard corpora.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Comparing phonemes and visemes with DNN-based lipreading
There is debate if phoneme or viseme units are the most effective for a lipreading system. Some studies use phoneme units even though phonemes describe unique short sounds; other studies tried to improve lipreading accur…
DecoderLipreadingImproving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). How…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionLLM-based phoneme-to-grapheme for phoneme-based speech recognition
In automatic speech recognition (ASR), phoneme-based multilingual pre-training and crosslingual fine-tuning is attractive for its high data efficiency and competitive results compared to subword-based models. However, We…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognition+2Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, t…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionMlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers
In this article we present the design and the development of a knowledge based computational linguistic tool, Mlphon for Malayalam language. Mlphon computationally models linguistic rules using finite state transducers a…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DiversityGrapheme-to-Phoneme Conversion+10