Search Results for author:
Found 10 papers, 4 papers with code
Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units
End-to-end (E2E) keyword search (KWS) has emerged as an alternative and complimentary approach to conventional keyword search which depends on the output of automatic speech recognition (ASR) systems.
Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models
This paper explores speculative speech recognition (SSR), where we empower conventional automatic speech recognition (ASR) with speculation capabilities, allowing the recognizer to run ahead of audio.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Written Term Detection Improves Spoken Term Detection
End-to-end (E2E) approaches to keyword search (KWS) are considerably simpler in terms of training and indexing complexity when compared to approaches which use the output of automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations
Conventional keyword search systems operate on automatic speech recognition (ASR) outputs, which causes them to have a complex indexing and search pipeline.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
On-the-fly Text Retrieval for End-to-End ASR Adaptation
End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model.
USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder
There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without incurring the extra cost of evaluating an external language model at inference time.
End-to-End Open Vocabulary Keyword Search
Recently, neural approaches to spoken content retrieval have become popular.
Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings
Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length.
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it.
Bayesian Subspace HMM for the Zerospeech 2020 Challenge
In this paper we describe our submission to the Zerospeech 2020 challenge, where the participants are required to discover latent representations from unannotated speech, and to use those representations to perform speech synthesis, with synthesis quality used as a proxy metric for the unit quality.
