Sentence boundary detection in chinese broadcast news using conditional random fields and prosodic features

Xu, Chenglin; Xie, Lei; Fu, Zhonghua

doi:10.1109/chinasip.2014.6889197

Cited by 6 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works (e.g., Stolcke and Shriberg, 1996, Wang and Narayanan, 2004, and Liu et al, 2006 use the Switchboard corpus to identify syntactically-based prosodic boundaries in telephone conversations between strangers, using orthographic inputs and/or manually crafted acoustic features. Xu et al (2014) applies pause, pitch, energy, and duration information to a similar task in spoken Mandarin. More recent work has pursued integrated approaches that consider Speech-To-Text (STT) transcription and segmentation simultaneously, but still have not focused on IU boundaries in conversational speech.…”

Section: Introductionmentioning

confidence: 99%

PSST! Prosodic Speech Segmentation with Transformers

Roll,

Graham,

Todd

2023

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

We develop and probe a model for detecting the boundaries of prosodic chunks in untranscribed conversational English speech. The model is obtained by fine-tuning a Transformer-based speech-to-text (STT) model to integrate the identification of Intonation Unit (IU) boundaries with the STT task. The model shows robust performance, both on held-out data and on out-of-distribution data representing different dialects and transcription protocols. By evaluating the model on degraded speech data, and comparing it with alternatives, we establish that it relies heavily on lexico-syntactic information inferred from audio, and not solely on acoustic information typically understood to cue prosodic structure. We release our model 1 as both a transcription tool and a baseline for further improvements in prosodic segmentation.

show abstract

Section: Introductionmentioning

confidence: 99%

PSST! Prosodic Speech Segmentation with Transformers

Roll,

Graham,

Todd

2023

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

View full text Add to dashboard Cite

show abstract

“…Nicola et al [2] studied various lexical features, including language model features, sentence length features and syntax features, on different genres ranging from formal newspaper text to informal, dictated messages, and from written text to spoken transcript. Recent efforts have shown that speech prosody, especially pause and pitch related features, are informative indicators for structural events [1, 3,4,5] including sentence boundaries [6,7,8,9]. Research has shown that a decision tree (DT) model learned from prosodic features can achieve comparable performance with that learned from lexical features.…”

Section: Introductionmentioning

confidence: 99%

A deep neural network approach for sentence boundary detection in broadcast news

Xu¹,

Xie²,

Huang³

et al. 2014

Interspeech 2014

Self Cite

View full text Add to dashboard Cite

This paper presents a deep neural network (DNN) approach to sentence boundary detection in broadcast news. We extract prosodic and lexical features at each inter-word position in the transcripts and learn a sequential classifier to label these positions as either boundary or non-boundary. This work is realized by a hybrid DNN-CRF (conditional random field) architecture. The DNN accepts prosodic feature inputs and non-linearly maps them into boundary/non-boundary posterior probability outputs. Subsequently, the posterior probabilities are combined with lexical features and the integrated features are modeled by a linear-chain CRF. The CRF finally labels the inter-word positions as boundary or non-boundary by Viterbi decoding. Experiments show that, as compared with the state-of-the-art DT-CRF approach [1], the proposed DNN-CRF approach achieves 16.7% and 4.1% reduction in NIST boundary detection error in reference and speech recognition transcripts, respectively.

show abstract

mentioning

confidence: 99%

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

2023

View full text Add to dashboard Cite

Language models (LMs) have been argued to overlap substantially with human beings in grammaticality judgment tasks. But when humans systematically make errors in language processing, should we expect LMs to behave like cognitive models of language and mimic human behavior? We answer this question by investigating LMs' more subtle judgments associated with "language illusions" -sentences that are vague in meaning, implausible, or ungrammatical but receive unexpectedly high acceptability judgments by humans. We looked at three illusions: the comparative illusion (e.g. "More people have been to Russia than I have"), the depth-charge illusion (e.g. "No head injury is too trivial to be ignored"), and the negative polarity item (NPI) illusion (e.g. "The hunter who no villager believed to be trustworthy will ever shoot a bear"). We found that probabilities represented by LMs were more likely to align with human judgments of being "tricked" by the NPI illusion which examines a structural dependency, compared to the comparative and the depth-charge illusions which require sophisticated semantic understanding. No single LM or metric yielded results that are entirely consistent with human behavior. Ultimately, we show that LMs are limited both in their construal as cognitive models of human language processing and in their capacity to recognize nuanced but critical information in complicated language materials.

show abstract

Sentence boundary detection in chinese broadcast news using conditional random fields and prosodic features

Cited by 6 publications

References 20 publications

PSST! Prosodic Speech Segmentation with Transformers

PSST! Prosodic Speech Segmentation with Transformers

A deep neural network approach for sentence boundary detection in broadcast news

Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

Contact Info

Product

Resources

About