A multiplatform speech recognition decoder based on weighted finite-state transducers

Stoimenov, Emilian; Schultz, Tanja

doi:10.1109/asru.2009.5373404

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Search space for a forced aligner is in terms of considering alternate pronunciations and fillers in between the words. By a pre-compilation of the search space, FST is expected to help improve decoding efficiency [6].…”

Section: Generating Fst To Deal With Alternate Pronunciation and Fmentioning

confidence: 99%

Better phone alignment for confidence measures in voice based querying

Prajapati

Tulsiani

Gada

et al. 2014

2014 Twentieth National Conference on Communications (NCC)

View full text Add to dashboard Cite

Voice-based querying for information is a powerful technology that can hugely enhance the scope of information retrieval systems by enabling their remote access via the ubiquitous mobile phone. Information retrieval based on automatic speech recognition however is challenging due to the environment noise and speaker idiosyncrasies typical of real-world scenarios. Wherever possible, strong domain constraints on the language model are used to minimize the impact of signal degradation on recognizer performance. This can lead to grossly mismatched utterance and hypothesis occasionally, a situation that must be detected to protect the call from irrecoverable errors. We consider the revalidation of recognition hypotheses via confidence measures derived from forced alignment using an independent decoder. We show that our FST based aligner can accurately reject incorrect decoder hypotheses while being particularly robust to the phenomenon of incomplete utterances.

show abstract

Section: Generating Fst To Deal With Alternate Pronunciation and Fmentioning

confidence: 99%

Better phone alignment for confidence measures in voice based querying

Prajapati

Tulsiani

Gada

et al. 2014

2014 Twentieth National Conference on Communications (NCC)

View full text Add to dashboard Cite

show abstract

It's not you, it's me: Automatically extracting social meaning from speed dates

Jurafsky¹

2009

2009 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding

View full text Add to dashboard Cite

Automatically detecting human social intentions from spoken conversation is an important task for social computing and for dialogue systems. We describe a system for detecting elements of interactional style: whether a speaker is awkward, friendly, or flirtatious. We create and use a new spoken corpus of 991 4-minute speed-dates. Participants rated themselves and each other for these elements of style. Using rich dialogue, lexical, and prosodic features, we are able to detect flirtatious, awkward, and friendly styles in noisy natural conversational data with above 70% accuracy, significantly outperforming not only the baseline but also, for flirtation, outperforming the human interlocutors. We find that features like pitch, energy, and the use of emotional vocabulary help detect flirtation, collaborative conversational style (laughter, questions, collaborative completions) help in detecting friendliness, and disfluencies help in detecting awkwardness. In analyzing why our system outperforms humans, we show that humans are very poor perceivers of flirtatiousness in this task, and instead often project their own intended behavior onto their interlocutors. This talk describes joint work with Dan McFarland (School of Education) and Rajesh Ranganath (Computer Science Department).978-1-4244-5480-8/09/$26.00

show abstract

A multiplatform speech recognition decoder based on weighted finite-state transducers

Cited by 2 publications

References 18 publications

Better phone alignment for confidence measures in voice based querying

Better phone alignment for confidence measures in voice based querying

It's not you, it's me: Automatically extracting social meaning from speed dates

Contact Info

Product

Resources

About