Advancing Connectionist Temporal Classification With Attention Modeling
In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time convolution features to model attention as part of the CTC network. To further improve attention modeling, we utilize content information extracted from a network representing an implicit language model. Finally, we introduce vector based attention weights that are applied on context vectors across both time and their individual components. We evaluate our system on a 3400 hours Microsoft Cortana voice assistant task and demonstrate that our proposed model consistently outperforms the baseline model achieving about 20% relative reduction in word error rates.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationLanguage ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Advancing Speech Recognition With No Speech Or With Noisy Speech
In this paper we demonstrate end-to-end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and conne…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)EEGElectroencephalogram (EEG)+3Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition
The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To impr…
Decoderspeech-recognitionSpeech RecognitionSelf-Attention Networks for Connectionist Temporal Classification in Speech Recognition
The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-…
ClassificationDecoderGeneral ClassificationGPU+3End-to-End Text-to-Speech using Latent Duration based on VQ-VAE
Explicit duration modeling is a key to achieving robust and efficient alignment in text-to-speech synthesis (TTS). We propose a new TTS framework using explicit duration modeling that incorporates duration as a discrete …
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisAdvancing Acoustic-to-Word CTC Model with Attention and Mixed-Units
The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the curren…
DecoderLanguage ModelingLanguage Modelling