On the robust automatic segmentation of spontaneous speech

The results from applying an improved algorithm to the task of automatic segmentation of spontaneous telephone quality speech are presented, and compared to the results from those resulting from superimposing white noise. Three segmentation algorithms are compared which are all based on variants of the Spectral Variation Function. Experimental results are obtained on the OGI multi language telephone speech corpus (OGLTS). We show that the use of the auditory forward and backward masking effects prior to the SVF computation increases the robustness of the algorithm to white noise. When the average signal to noise ratio (SNR) is decreased to 10 dB, the peak ratio (defined as the ratio of the number of peaks measured at the target over the original SNRs) is increased by 16%, 12%, and 11% for the MFC (Mel Frequency Cepstra), RASTA (Relative Spectral Processing), and the FBDYN (Forward Backward Auditory Masking Dynamic Cepstra) SVF segmentation algorithms, respectively.

• Publication year

  1996

• Venue

  Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96

• Publication date

  1996-10-03

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICSLP.1996.607750
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Spontaneous speech recognition using dynamic CEPSTRA incorporating forward and backward masking effect

  1995cited by this paper
• A dynamic cepstrum incorporating time-frequency masking and its application to continuous speech recognition

  1993cited by this paper
• The OGI multi-language telephone speech corpus

  1992cited by this paper
• RASTA-PLP speech analysis technique

  1992cited by this paper
• Segment based variable frame rate speech analysis and recognition using a spectral variation function

  1992influential reference
• On the automatic segmentation of speech signals

  1987cited by this paper
• An investigation on the use of acoustic sub-word units for automatic speech recognition

  1987cited by this paper
• Speaker-independent isolated word recognition using dynamic features of speech spectrum

  1986cited by this paper

• ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling

  2026cites this paper
• Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?

  2025cites this paper
• End-to-End Simultaneous Speech Translation with Differentiable Segmentation

  2023cites this paper
• Summary and Future Work

  2022cites this paper
• Speechlike Signal Synthesis Module For Information Security Systems

  2020cites this paper
• Automatic syllable segmentation algorithm of Chinese speech based on MF-DFA

  2017cites this paper
• Medidas de información multiresolución aplicadas al procesamiento de señales de habla

  2017cites this paper
• Contributions à l'étude et à la reconnaissance automatique de la parole en Fongbe

  2016cites this paper
• Syllable based speech analysis fo affective robotics

  2013cites this paper
• Sequential method for speech segmentation based on Random Matrix Theory

  2013cites this paper
• Blind Segmentation of Speech Using Non-Linear Filtering Methods

  2011cites this paper
• Speech segmentation using regression fusion of boundary predictions

  2010cites this paper
• An improved speech segmentation quality measure: the r-value

  2009cites this paper
• A computational model for unsupervised childlike speech acquisition

  2009cites this paper
• SONORITY BASED SYLLABLE SEGMENTATION

  2009cites this paper
• Automatic determination of sub-word units for automatic speech recognition

  2008cites this paper
• Phonetic segmentation using multiple speech features

  2008cites this paper
• A new approach for phoneme segmentation of speech signals

  2007cites this paper
• Speech Segmentation and Clustering Methods for a New Speech Recognition Architecture

  2007cites this paper
• Finding Maximum Margin Segments in Speech

  2007cites this paper
• Broad Phonemic Class Segmentation of Speech Signals in Noise Environments

  2006cites this paper
• Automatic Segmentation of Greek Speech Signals to Broad Phonemic Classes

  2006cites this paper
• Evaluation of implicit broad phonemic segmentation of speech signals using pitchmarks

  2006cites this paper
• On the Processing of Fuzzy Patterns for Text Independent Phonetic Speech Segmentation

  2006cites this paper
• Multisensor Segmentation-based Noise Suppression for Intelligibility Improvement in MELP Coders

  2006cites this paper
• Text Independent Methods for Speech Segmentation

  2004cites this paper
• A JAVA interface for speech analysis and segmentation

  2003cites this paper
• Automatic Parameter Estimation for a Context-Independent Speech Segmentation Algorithm

  2002cites this paper
• From Synapses to Rules

  2002cites this paper
• An user-friendly interface for text-independent phoneme segmentation

  2002cites this paper
• A new text-independent method for phoneme segmentation

  2001cites this paper
• Automatic time alignment of phonemes using acoustic-phonetic information

  2000cites this paper
• Speaker verification in a time-feature space

  1999cites this paper
• Automatic segmentation of speech recorded in unknown noisy channel characteristics

  1998cites this paper
• A duration-based confidence measure for automatic segmentation of noise corrupted speech

  1998cites this paper
• Data-driven design of RASTA-like filters

  1997cites this paper