Combining Spectral Representations for Large Vocabulary Continuous Speech Recognition

Giulia Garau, Steve Renals

Research output: Contribution to journalArticlepeer-review


In this paper we investigate the combination of complementary acoustic feature streams in large vocabulary continuous speech recognition (LVCSR). We have explored the use of acoustic features obtained using a pitch-synchronous analysis, STRAIGHT, in combination with conventional features such as mel frequency cepstral coefficients. Pitch-synchronous acoustic features are of particular interest when used with vocal tract length normalisation (VTLN) which is known to be affected by the fundamental frequency. We have combined these spectral representations directly at the acoustic feature level using heteroscedastic linear discriminant analysis (HLDA) and at the system level using ROVER. We evaluated this approach on three LVCSR tasks: dictated newspaper text (WSJCAM0), conversational telephone speech (CTS), and multiparty meeting transcription. The CTS and meeting transcription experiments were both evaluated using standard NIST test sets and evaluation protocols. Our results indicate that combining conventional and pitch-synchronous acoustic feature sets using HLDA results in a consistent, significant decrease in word error rate across all three tasks. Combining at the system level using ROVER resulted in a further significant decrease in word error rate.
Original languageEnglish
Pages (from-to)508-518
Number of pages11
JournalIEEE Transactions on Audio, Speech and Language Processing
Issue number3
Publication statusPublished - Mar 2008


  • Feature combination
  • heteroscedastic linear discriminant analysis (HLDA)
  • large-vocabulary continuous speech recognition (LVCSR)
  • pitch-synchronous
  • vocal tract length normalization (VTLN)

Fingerprint Dive into the research topics of 'Combining Spectral Representations for Large Vocabulary Continuous Speech Recognition'. Together they form a unique fingerprint.

Cite this