Major progress is being recorded regularly on both the technology and exploitation of
automatic speech recognition (ASR) and spoken language systems. However, there are still …

Research on speech processing has traditionally considered the task of designing hand-
engineered acoustic features (feature engineering) as a separate distinct problem from the …

We explore unsupervised pre-training for speech recognition by learning representations of
raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting …

Is pushing numbers on a single benchmark valuable in automatic speech recognition?
Research results in acoustic modeling are typically evaluated based on performance on a …

The key problem to be faced when building a HMM-based continuous speech recogniser is
maintaining the balance between model complexity and available training data. For large …

In hidden Markov model (HMM) based automatic speech recognition (ASR) system,
modeling the statistical relationship between the acoustic speech signal and the HMM states …

Candidate answers responsive to a user query are analyzed using a natural language
engine to determine appropriate answers from an electronic database. The system and meth …

Primary Examiner Martin Lerner Related US Application Data(74) Attorney, Agent, or Firm
PatentBest; Andrew McAleavey (63) Continuation-in-part of application No. 09/439,145, filed …

HTK is an integrated suite of software tools for building and manipulating continuous density
Hidden Markov Models (HMMs). It consists of a set of library modules and a set of more than …

(57) ABSTRACT A real-time system incorporating speech recognition and lin guistic
processing for recognizing a spoken query by a user and distributed between client and …