Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
Transducer models have emerged as a promising choice for end-to-end ASR systems, offering a balanced trade-off between recognition accuracy, streaming capabilities, and inference speed in greedy decoding. However, beam search significantly slows down Transducers due to repeated evaluations of key network components, limiting practical applications. This paper introduces a universal method to accelerate beam search for Transducers, enabling the implementation of two optimized algorithms: ALSD++ and AES++. The proposed method utilizes batch operations, a tree-based hypothesis structure, novel blank scoring for enhanced shallow fusion, and CUDA graph execution for efficient GPU inference. This narrows the speed gap between beam and greedy modes to only 10-20% for the whole system, achieves 14-30% relative improvement in WER compared to greedy decoding, and improves shallow fusion for low-resource up to 11% compared to existing implementations. All the algorithms are open sourced.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Accelerating RNN Transducer Inference via One-Step Constrained Beam Search
We propose a one-step constrained (OSC) beam search to accelerate recurrent neural network (RNN) transducer (RNN-T) inference. The original RNN-T beam search has a while-loop leading to speed down of the decoding process…
Fast and parallel decoding for transducer
The transducer architecture is becoming increasingly popular in the field of speech recognition, because it is naturally streaming as well as high in accuracy. One of the drawbacks of transducer is that it is difficult t…
GPUspeech-recognitionSpeech RecognitionVQ-T: RNN Transducers using Vector-Quantized Prediction Network States
Beam search, which is the dominant ASR decoding algorithm for end-to-end models, generates tree-structured hypotheses. However, recent studies have shown that decoding with hypothesis merging can achieve a more efficient…
Language ModelingLanguage ModellingRNN-T For Latency Controlled ASR With Improved Beam Search
Neural transducer-based systems such as RNN Transducers (RNN-T) for automatic speech recognition (ASR) blend the individual components of a traditional hybrid ASR systems (acoustic model, language model, punctuation mode…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Computational EfficiencyLanguage Modeling+4Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition
Although frame-based models, such as CTC and transducers, have an affinity for streaming automatic speech recognition, their decoding uses no future knowledge, which could lead to incorrect pruning. Conversely, label-bas…
Automatic Speech RecognitionDecoderspeech-recognitionSpeech Recognition