On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings

Kolář, Jáchym; Shriberg, Elizabeth; Liu, Yang

doi:10.21437/interspeech.2006-551

Cited by 5 publications

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech

Kolář¹,

Liu²,

Shriberg³

2010

Speech Communication

Self Cite

View full text Add to dashboard Cite

Speaker-dependent modeling has a long history in speech recognition, but has received less attention in speech understanding. This study explores speaker-specific modeling for the task of automatic segmentation of speech into dialog acts (DAs), using a linear combination of speaker-dependent and speaker-independent language and prosodic models. Data come from 20 frequent speakers in the ICSI meeting corpus; adaptation data per speaker ranges from 5k to 115k words. We compare performance for both reference transcripts and automatic speech recognition output. We find that: (1) speaker adaptation in this domain results both in a significant overall improvement and in improvements for many individual speakers, (2) the magnitude of improvement for individual speakers does not depend on the amount of adaptation data, and (3) language and prosodic models differ both in degree of improvement, and in relative benefit for specific DA classes. These results suggest important future directions for speaker-specific modeling in spoken language understanding tasks.

show abstract

Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech

Kolář¹,

Liu²,

Shriberg³

2010

Speech Communication

Self Cite

View full text Add to dashboard Cite

show abstract

Impact of automatic sentence segmentation on meeting summarization

Liu

Xie

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

This paper investigates the impact of automatic sentence segmentation on speech summarization using the ICSI meeting corpus. We use a hidden Markov model (HMM) for sentence segmentation that integrates the N-gram language model and pause information, and a maximum marginal relevance (MMR) based extractive summarization method. The system-generated summaries are compared to multiple human summaries using the ROUGE scores. The decision thresholds from the segmentation system are varied to examine the impact of different segments on summarization. We find that (1) using system generated utterance segments degrades summarization performance compared to using human annotated sentences; (2) segmentation needs to be optimized for summarization instead of the segmentation task itself, however, the patterns are slightly different from prior work for other tasks such as parsing; and (3) there are effects from different summarization evaluation metrics as well as speech recognition errors.

show abstract

Sentence segmentation for speech processing

Anu

Karjigi

2014

2014 IEEE National Conference on Communication, Signal Processing and Networking (NCCSN)

View full text Add to dashboard Cite

Automatic sentence segmentation of speech is a process of identifying the end of a sentence. It is used for improving the output after speech recognition and helps in making the recognition output more readable. It is generally a two-class problem which involves the identification of a boundary characterizing the sentence part and the non-sentence part. An Automatic Speech Recognition (ASR) system receives a stream of speech signal and produces a un-annotated stream of words. The regions of silences in the inter word boundaries of the output of ASR are detected. The prosodic features of the input speech signal that are given to the ASR are extracted for a particular duration of time which includes pause, rhyme, slope, minimum, maximum and mean features. Once the features are extracted, SVM classifier uses all the features and discriminates each word boundary as sentence or non-sentence boundary.

show abstract

On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings

Cited by 5 publications

References 16 publications

Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech

Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech

Impact of automatic sentence segmentation on meeting summarization

Sentence segmentation for speech processing

Contact Info

Product

Resources

About