The effect of language models on phonetic decoding for spoken term detection

Wallace, Roy; Baker, Bernadette; Vogt, Robbie; Sridharan, Sridha

doi:10.1145/1631127.1631132

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, ASR errors replacing a word by a semantically dissimilar word were shown to have more impact on retrieval performance than a word with close meaning [109]. Another interesting observation is that although better language models were shown to reduce the ASR error rate, this did not always translate to better STD performance [39], [110], [111]. This is probably because language models tend to bias the decoding towards word sequences frequently appearing in the training data of the language models, but in the training data the terminologies or topic-specific terms often used in the queries are usually rare [111].…”

Section: Modified Speech Recognition For Retrieval Purposesmentioning

confidence: 99%

“…Another interesting observation is that although better language models were shown to reduce the ASR error rate, this did not always translate to better STD performance [39], [110], [111]. This is probably because language models tend to bias the decoding towards word sequences frequently appearing in the training data of the language models, but in the training data the terminologies or topic-specific terms often used in the queries are usually rare [111]. In addition, because usually lattices instead of one-best transcripts are used in spoken content retrieval, expected error rate defined over the lattices should be in principle a better predictor of retrieval performance than the error rate of one-best transcriptions [112].…”

Section: Modified Speech Recognition For Retrieval Purposesmentioning

confidence: 99%

See 1 more Smart Citation

Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval

Lee

Glass

Lee

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

101

View full text Add to dashboard Cite

Spoken content retrieval refers to directly indexing and retrieving spoken content based on the audio rather than text descriptions. This potentially eliminates the requirement of producing text descriptions for multimedia content for indexing and retrieval purposes, and is able to precisely locate the exact time the desired information appears in the multimedia. Spoken content retrieval has been very successfully achieved with the basic approach of cascading automatic speech recognition (ASR) with text information retrieval: after the spoken content is transcribed into text or lattice format, a text retrieval engine searches over the ASR output to find desired information. This framework works well when the ASR accuracy is relatively high, but becomes less adequate when more challenging real-world scenarios are considered, since retrieval performance depends heavily on ASR accuracy. This challenge leads to the emergence of another approach to spoken content retrieval: to go beyond the basic framework of cascading ASR with text retrieval in order to have retrieval performances that are less dependent on ASR accuracy. This overview article is intended to provide a thorough overview of the concepts, principles, approaches, and achievements of major technical contributions along this line of investigation. This includes five major directions: 1) Modified ASR for Retrieval Purposes: cascading ASR with text retrieval, but the ASR is modified or optimized for spoken content retrieval purposes; 2) Exploiting the Information not present in ASR outputs: to try to utilize the information in speech signals inevitably lost when transcribed into phonemes and words; 3) Directly Matching at the Acoustic Level without ASR: for spoken queries, the signals can be directly matched at the acoustic level, rather than at the phoneme or word levels, bypassing all ASR issues; 4) Semantic Retrieval of Spoken Content: trying to retrieve spoken content that is semantically related to the query, but not necessarily including the query terms themselves; 5) Interactive Retrieval and Efficient Presentation of the Retrieved Objects: with efficient presentation of the retrieved objects, an interactive retrieval process incorporating user actions may produce better retrieval results and user experiences.Index Terms-Spoken content retrieval, spoken term detection, query by example, semantic retrieval, joint optimization, pseudo-relevance feedback, graph-based random walk, unsupervised acoustic pattern discovery, query expansion, interactive retrieval, summarization, key term extraction.

show abstract

Section: Modified Speech Recognition For Retrieval Purposesmentioning

confidence: 99%

Section: Modified Speech Recognition For Retrieval Purposesmentioning

confidence: 99%

Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval

Lee

Glass

Lee

et al. 2015

IEEE/ACM Trans. Audio Speech Lang. Process.

101

View full text Add to dashboard Cite

show abstract

“…The deal with this problem, a combination of phoneme recognition and LVCSR output was proposed [15], [16]. In addition, Wallace et al [17] proposed a language modeling method for improving the phoneme recognition.…”

Section: Related Workmentioning

confidence: 99%

Spoken Term Detection Using Phoneme Transition Network from Multiple Speech Recognizers' Outputs

Natori

Furuya

Nishizaki

et al. 2013

Journal of Information Processing

View full text Add to dashboard Cite

Spoken Term Detection (STD) that considers the out-of-vocabulary (OOV) problem has generated significant interest in the field of spoken document processing. This study describes STD with false detection control using phoneme transition networks (PTNs) derived from the outputs of multiple speech recognizers. PTNs are similar to subword-based confusion networks (CNs), which are originally derived from a single speech recognizer. Since PTNformed index is based on the outputs of multiple speech recognizers, it is robust to recognition errors. Therefore, PTN should also be robust to recognition errors in an STD task, when compared to the CN-formed index from a single speech recognition system. Our PTN-formed index was evaluated on a test collection. The experiment showed that the PTN-based approach effectively detected OOV terms, and improved the F-measure value from 0.370 to 0.639 when compared with a baseline approach. Furthermore, we applied two false detection control parameters, one is based on the majority voting scheme. The other is a measure of the ambiguity of CN, to the calculation of detection score. By introducing these parameters, the performance of STD was found to be better (0.736 for the F-measure value) than that without any parameters (0.639).

show abstract

Improved dynamic match phone lattice search for Persian spoken term detection system in online and offline applications

Tabibian

Akbari

Nasersharif

2019

Int J Speech Technol

View full text Add to dashboard Cite

The effect of language models on phonetic decoding for spoken term detection

Cited by 4 publications

References 8 publications

Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval

Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval

Spoken Term Detection Using Phoneme Transition Network from Multiple Speech Recognizers' Outputs

Improved dynamic match phone lattice search for Persian spoken term detection system in online and offline applications

Contact Info

Product

Resources

About