Highly spontaneous, conversational, and potentially emotional and noisy speech is known to be a challenge for today's automatic speech recognition (ASR) systems, which highlights the need for advanced algorithms that improve speech features and models. Histogram Equalization is an efficient method to reduce the mismatch between clean and noisy conditions by normalizing all moments of the probability distribution of the feature vector components. In this article, we propose to combine histogram equalization and multi-condition training for robust keyword detection in noisy speech. To better cope with conversational speaking styles, we show how contextual information can be effectively exploited in a multi-stream ASR framework that dynamically models context-sensitive phoneme estimates generated by a long short-term memory neural network. The proposed techniques are evaluated on the SEMAINE database-a corpus containing emotionally colored conversations with a cognitive system for "Sensitive Artificial Listening".

Multi-Stream LSTM-HMM Decoding and Histogram Equalization for Noise Robust Keyword Spotting / Woellmer, M.; Marchi, E.; Squartini, Stefano; Schuller, B.. - In: COGNITIVE NEURODYNAMICS. - ISSN 1871-4080. - Volume 5, Issue 3:(2011), pp. 253-264. [10.1007/s11571-011-9166-9]

Multi-Stream LSTM-HMM Decoding and Histogram Equalization for Noise Robust Keyword Spotting

SQUARTINI, Stefano;
2011-01-01

Abstract

Highly spontaneous, conversational, and potentially emotional and noisy speech is known to be a challenge for today's automatic speech recognition (ASR) systems, which highlights the need for advanced algorithms that improve speech features and models. Histogram Equalization is an efficient method to reduce the mismatch between clean and noisy conditions by normalizing all moments of the probability distribution of the feature vector components. In this article, we propose to combine histogram equalization and multi-condition training for robust keyword detection in noisy speech. To better cope with conversational speaking styles, we show how contextual information can be effectively exploited in a multi-stream ASR framework that dynamically models context-sensitive phoneme estimates generated by a long short-term memory neural network. The proposed techniques are evaluated on the SEMAINE database-a corpus containing emotionally colored conversations with a cognitive system for "Sensitive Artificial Listening".
2011
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11566/62533
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 9
social impact