Topic Identification for Speech without ASR

03/22/2017
by   Chunxi Liu, et al.
0

Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the manually transcribed speech required to develop standard ASR systems can be severely limited or unavailable. In this paper, we investigate alternative unsupervised solutions to obtaining tokenizations of speech in terms of a vocabulary of automatically discovered word-like or phoneme-like units, without depending on the supervised training of ASR systems. Moreover, using automatic phoneme-like tokenizations, we demonstrate that a convolutional neural network based framework for learning spoken document representations provides competitive performance compared to a standard bag-of-words representation, as evidenced by comprehensive topic ID evaluations on both single-label and multi-label classification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/29/2021

Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?

Spoken language understanding (SLU) tasks are usually solved by first tr...
research
07/21/2023

Topic Identification For Spontaneous Speech: Enriching Audio Features With Embedded Linguistic Information

Traditional topic identification solutions from audio rely on an automat...
research
04/13/2019

M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding

Deep learning is at the core of recent spoken language understanding (SL...
research
06/16/2021

Topic Classification on Spoken Documents Using Deep Acoustic and Linguistic Features

Topic classification systems on spoken documents usually consist of two ...
research
04/24/2021

Language ID Prediction from Speech Using Self-Attentive Pooling and 1D-Convolutions

This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on pr...
research
04/08/2020

Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech

This paper considers the impact of automatic segmentation on the fully-a...
research
07/01/2019

Improving Performance of End-to-End ASR on Numeric Sequences

Recognizing written domain numeric utterances (e.g. I need 1.25.) can be...

Please sign up or login with your details

Forgot password? Click here to reset