Search Results for author:
Found 21 papers, 1 papers with code
O-1: Self-training with Oracle and 1-best Hypothesis
O-1 achieves 13\% to 25\% relative improvement over EMBR on the various datasets that SpeechStew comprises of, and a 12\% relative gap reduction with respect to the oracle WER over EMBR training on the in-house dataset.
Large-scale Language Model Rescoring on Long-form Data
In this work, we study the impact of Large-scale Language Models (LLM) on Automated Speech Recognition (ASR) of YouTube videos, which we use as a source for long-form ASR.
Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Soft distillation is another popular KD method that distills the output logits of the teacher model.
Modular Hybrid Autoregressive Transducer
In this work, we propose a modular hybrid autoregressive transducer (MHAT) that has structurally separated label and blank decoders to predict label and blank distributions, respectively, along with a shared acoustic encoder.
Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition
We investigate a few approaches to increasing attention head diversity, including using different attention mechanisms for each head and auxiliary training loss functions to promote head diversity.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems
Assuming we have additional text-to-intent data (without speech) available, we investigated two techniques to improve the S2I system: (1) transfer learning, in which acoustic embeddings for intent classification are tied to fine-tuned BERT text embeddings; and (2) data augmentation, in which the text-to-intent data is converted into speech-to-intent data using a multi-speaker text-to-speech system.
End-to-End Spoken Language Understanding Without Full Transcripts
For our speech-to-entities experiments on the ATIS corpus, both the CTC and attention models showed impressive ability to skip non-entity words: there was little degradation when trained on just entities versus full transcripts.
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos
Further, we propose a tri-modal model that jointly processes raw audio, video, and text captions from videos to learn a multi-modal semantic embedding space useful for text-video retrieval.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard
It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition models are competitive with hybrid models only when a large amount of data, at least a thousand hours, is available for training.
Ranked #2 on
Speech Recognition
on swb_hub_500 WER fullSWBCH
Challenging the Boundaries of Speech Recognition: The MALACH Corpus
This paper proposes that the community place focus on the MALACH corpus to develop speech recognition systems that are more robust with respect to accents, disfluencies and emotional speech.
Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single model with knowledge distillation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Building competitive direct acoustics-to-word models for English conversational speech recognition
This is because A2W models recognize words from speech without any decoder, pronunciation lexicon, or externally-trained language model, making training and decoding with such models simple.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Our CTC word model achieves a word error rate of 13. 0%/18. 8% on the Hub5-2000 Switchboard/CallHome test sets without any LM or decoder compared with 9. 6%/16. 0% for phone-based CTC with a 4-gram LM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
English Conversational Telephone Speech Recognition by Humans and Machines
This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates?
Ranked #3 on
Speech Recognition
on Switchboard + Hub500
End-to-End ASR-free Keyword Search from Speech
The first sub-system is a recurrent neural network (RNN)-based acoustic auto-encoder trained to reconstruct the audio through a finite-dimensional representation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Invariant Representations for Noisy Speech Recognition
Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not seen during training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Diverse Embedding Neural Network Language Models
We propose Diverse Embedding Neural Network (DENN), a novel architecture for language models (LMs).
Generalized Ambiguity Decomposition for Understanding Ensemble Diversity
We present extensions of this decomposition to common regression and classification loss functions, and report a simulation-based analysis of the diversity term and the accuracy of the decomposition.
