Combination of search techniques for improved spotting of OOV keywords

Karakos, Damianos; Schwartz, Richard

doi:10.1109/icassp.2015.7178990

Cited by 11 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experiments, we observed that filtering the probability scores with a moving average filter of window width W and uniform weights 1 W improves the STD performance. The effect of this filtering is evaluated in Sec.…”

Section: Std Algorithmmentioning

confidence: 97%

“…By recognizing and pre-indexing the spoken utterances the in-vocabulary (IV) queries could be directly found in the word index. The handling of out-ofvocabulary (OOV) terms consists of a much wider spectrum of methods [1] including recognition and indexing of sub-word units (phonemes, syllables or word fragments) [2,3,4], the use of IV proxy words [5,6] or the use of acoustic embeddings and similarity metrics in a vector space [7,8]. The acoustic embeddings often play a role also in the query-by-example (QbE) task in the low-resourced setup but the idea of neural-network-based projection of the query and the utterance into a single space could be reused in the more general STD task employing the standard speech recognition models [9,10,11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Švec¹,

Šmídl²,

Psutka³

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

The paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a spoken term and estimate its relevance score. The phoneme confusion network generated by a phoneme recognizer is processed by the deep LSTM network which projects each segment of the confusion network into an embedding space. The searched term is projected into the same embedding space using another deep LSTM network. The relevance score is then computed using a simple dot-product in the embedding space and calibrated using a sigmoid function to predict the probability of occurrence. The location of the searched term is then estimated from the sequence of output probabilities. The deep LSTM networks are trained in a self-supervised manner from paired recognition hypotheses on word and phoneme levels. The method is experimentally evaluated on MALACH data in English and Czech languages.

show abstract

Section: Std Algorithmmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Švec¹,

Šmídl²,

Psutka³

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

show abstract

“…The 1-best grapheme hypothesis H and the alignment A is used as pivot sequence in confusion network generation [15], i.e. the alternative graphemes are added parallel for each 1 Here we use the interval notation also for the integer intervals:…”

Section: Grapheme Confusion Networkmentioning

confidence: 99%

“…The spoken term detection (STD) task is a widely studied field of speech processing. The STD emerged as a variant of traditional keyword spotting which speeds up the search phase by offline pre-processing and indexing of the searched data [1], where the pre-processing costs are counterweighted by the speed of an online search. A conventional approach to STD is to use the DNN-HMM hybrid speech recognizer to transform the input audio data into a set of word lattices from which the inverted word index is built.…”

Section: Introductionmentioning

confidence: 99%

Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer

Švec¹,

Lehečka²,

Šmídl³

2022

Interspeech 2022

View full text Add to dashboard Cite

In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised pretraining approach combined with transfer learning of the fine-tuned speech recognizer. Since it lacks the pronunciation vocabulary and language model, the approach is suitable for tasks where obtaining such models is not easy or almost impossible.In this paper, we use the Wav2Vec speech recognizer in the task of spoken term detection over a large set of spoken documents. The method employs a deep LSTM network which maps the recognized hypothesis and the searched term into a shared pronunciation embedding space in which the term occurrences and the assigned scores are easily computed.The paper describes a bootstrapping approach that allows the transfer of the knowledge contained in traditional pronunciation vocabulary of DNN-HMM hybrid ASR into the context of grapheme-based Wav2Vec. The proposed method outperforms the previously published system based on the combination of the DNN-HMM hybrid ASR and phoneme recognizer by a large margin on the MALACH data in both English and Czech languages.

show abstract

“…Score normalization is crucial for the right balance between true positives and false alarms. In this work, the raw scores are first normalized with a linear fit model, after which keyword-specific thresholding and exponential normalization (KST) is applied [23].…”

Section: Kws Systemmentioning

confidence: 99%

Machine translation based data augmentation for Cantonese keyword spotting

Huang

Gorin

Gauvain

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper presents a method to improve a language model for a limited-resourced language using statistical machine translation from a related language to generate data for the target language. In this work, the machine translation model is trained on a corpus of parallel Mandarin-Cantonese subtitles and used to translate a large set of Mandarin conversational telephone transcripts to Cantonese, which has limited resources. The translated transcripts are used to train a more robust language model for speech recognition and for keyword search in Cantonese conversational telephone speech. This method enables the keyword search system to detect 1.5 times more out-of-vocabulary words, and achieve 1.7% absolute improvement on actual term-weighted value.

show abstract

Combination of search techniques for improved spotting of OOV keywords

Cited by 11 publications

References 17 publications

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer

Machine translation based data augmentation for Cantonese keyword spotting

Contact Info

Product

Resources

About