Browsing by Author "Wolf, Martin"

Now showing items 1-6 of 6

    • Channel selection and reverberation-robust automatic speech recognition 

      Wolf, Martin (Universitat Politècnica de Catalunya, 2013-11-11)
      Doctoral thesis
      Open Access
      If speech is acquired by a close-talking microphone in a controlled and noise-free environment, current state-of-the-art recognition systems often show an acceptable error rate. The use of close-talking microphones, however, ...

    • Channel selection measures for multi-microphone speech recognition 

      Nadeu Camprubí, Climent; Wolf, Martin (2014-02-01)
      Article
      Restricted access - publisher's policy
      Automatic speech recognition in a room with distant microphones is strongly affected by noise and reverberation. In scenarios where the speech signal is captured by several arbitrarily located microphones the degree of ...

    • Channel selection using N-best hypothesis for multi-microphone ASR 

      Wolf, Martin; Nadeu Camprubí, Climent (2013)
      Conference report
      Restricted access - publisher's policy
      If speech is captured by several arbitrarily-located microphones in a room, the degree of distortion by noise and reverberation may vary strongly from one channel to another. Channel selection for automatic speech recognition ...

    • Extension of the remos concept to frequency-filtering-based features for reverberation-robust speech recognition 

      Maas, Roland; Wolf, Martin; Sehr, Armin; Nadeu Camprubí, Climent; Kellermann, Walter (2011)
      Conference report
      Restricted access - publisher's policy
      The introduction of partly decorrelated features into the REMOS (REverberationMOdeling for Speech recognition) concept for distant-talking speech recognition [1] is discussed. REMOS combines a hidden Markov model (HMM), ...

    • Model-based processing for acoustic scene analysis 

      Nadeu Camprubí, Climent; Chakraborty, Rupayan; Wolf, Martin (Institute of Electrical and Electronics Engineers (IEEE), 2014)
      Conference report
      Restricted access - publisher's policy
      The analysis of acoustic scenes requires several functionalities, being perhaps recognition (speech, speaker, other acoustic events) and spatial localization the two most relevant ones. For a reduced invasiveness, ...

    • On the potential of channel selection for recognition of reverberated speech with multiple microphones 

      Wolf, Martin; Nadeu Camprubí, Climent (2010)
      Conference report
      Open Access
      The performance of ASR systems in a room environment with distant microphones is strongly affected by reverberation. As the degree of signal distortion varies among acoustic channels (i.e. microphones), the recognition ...