Search Results for author:
Found 10 papers, 2 papers with code
4D ASR: Joint Beam Search Integrating CTC, Attention, Transducer, and Mask Predict Decoders
Experimental results demonstrate that the jointly trained 4D model outperforms the E2E-ASR models trained with only one individual decoder.
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.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Contextualized Automatic Speech Recognition with Dynamic Vocabulary
Deep biasing (DB) improves the performance of end-to-end automatic speech recognition (E2E-ASR) for rare words or contextual phrases using a bias list.
OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification
Inspired by the Open Whisper-style Speech Model (OWSM) project, we propose OWSM-CTC, a novel encoder-only speech foundation model based on Connectionist Temporal Classification (CTC).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
In this work, we aim to improve the performance and efficiency of OWSM without extra training data.
Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search
The proposed method can be trained effectively by combining a bias phrase index loss and special tokens to detect the bias phrases in the input speech data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
Pre-training speech models on large volumes of data has achieved remarkable success.
Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation
End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same pronunciation and part of speech that are spelled differently.
DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models
Knowledge distillation trains a small student model to mimic the behavior of a large teacher model.
4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders
The network architecture of end-to-end (E2E) automatic speech recognition (ASR) can be classified into several models, including connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention mechanism, and non-autoregressive mask-predict models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
