Improved punctuation recovery through combination of multiple speech streams

Miranda, J. M.; Neto, João Paulo; Black, Alan W.

doi:10.1109/asru.2013.6707718

Cited by 4 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many links into other fields such as linguistics, syntax, psychology and automatic speech recognition which include transcription systems for intonational phrase structure (i.e. the ToBI annotation method [14]), the relation between syntactic structure and pause insertion [15,16], psycholinguistic studies related to the effects of superfluous and missing prosodic breaks [17,18], and the recovery of punctuation in automatic speech recognition output for improved performance of spoken language translation systems [19,20].…”

Section: Introductionmentioning

confidence: 99%

Pause Prediction from Text for Speech Synthesis with User-Definable Pause Insertion Likelihood Threshold

Braunschweiler

Maia

2016

Interspeech 2016

View full text Add to dashboard Cite

Predicting the location of pauses from text is an important aspect for speech synthesizers. The accuracy of pause prediction can significantly influence both naturalness and intelligibility. Pauses which help listeners to better parse the synthesized speech into meaningful units are deemed to increase naturalness and intelligibility ratings, while pauses in unexpected or incorrect locations can reduce these ratings and cause confusion. This paper presents a multi-stage pause prediction approach including first prosodic chunk prediction, followed by a feature scoring algorithm and finally a pause sequence evaluation module. Preference tests showed that the new method outperformed a pauses-at-punctuation baseline while not yet matching human performance. In addition, the approach includes two more functionalities: (1) a user-specifiable pause insertion rate and (2) multiple output formats in the form of binary pauses, multi-level pauses or as a score reflecting pause strength.

show abstract

Section: Introductionmentioning

confidence: 99%

Pause Prediction from Text for Speech Synthesis with User-Definable Pause Insertion Likelihood Threshold

Braunschweiler

Maia

2016

Interspeech 2016

View full text Add to dashboard Cite

show abstract

“…Similar works deal with the punctuation generation problem by using statistical models of prosodic features [9], the combination of both textual and prosodic features based on adaptive boosting [18], and a cross-linguistic study of prosodic features through two different approaches for feature selection: a forward search wrapper and feature filtering [14]. Although not using prosodic features strictly speaking, [25] takes advantage of the transcriptions of multiple parallel speech streams in four different languages in order to increase punctuation generation accuracy.…”

Section: Related Workmentioning

confidence: 99%

Attentional Parallel RNNs for Generating Punctuation in Transcribed Speech

Öktem

Farrús

Wanner

2017

Statistical Language and Speech Processing

View full text Add to dashboard Cite

Abstract. Until very recently, the generation of punctuation marks for automatic speech recognition (ASR) output has been mostly done by looking at the syntactic structure of the recognized utterances. Prosodic cues such as breaks, speech rate, pitch intonation that influence placing of punctuation marks on speech transcripts have been seldom used. We propose a method that uses recurrent neural networks, taking prosodic and lexical information into account in order to predict punctuation marks for raw ASR output. Our experiments show that an attention mechanism over parallel sequences of prosodic cues aligned with transcribed speech improves accuracy of punctuation generation.

show abstract

Automatic formatted transcripts for videos

Pappu

Stent

2015

Interspeech 2015

View full text Add to dashboard Cite

Improved punctuation recovery through combination of multiple speech streams

Cited by 4 publications

References 11 publications

Pause Prediction from Text for Speech Synthesis with User-Definable Pause Insertion Likelihood Threshold

Pause Prediction from Text for Speech Synthesis with User-Definable Pause Insertion Likelihood Threshold

Attentional Parallel RNNs for Generating Punctuation in Transcribed Speech

Automatic formatted transcripts for videos

Contact Info

Product

Resources

About