Speech Recognition Grammars Research Articles

SPOKEN FREE−FORM PASSWORDS FOR LIGHT−WEIGHT SPEAKER VERIFICATION USING STANDARD SPEECH RECOGNITION ENGINES

The present invention discloses a system and a method for authenticating a user based upon a spoken password processed though a standard speech recognition engine lacking specialized speaker identification and verification (SIV) capabilities. It should be noted that the standard speech recognition grammar can be capable of acoustically generating speech recognition grammars in accordance with the cross referenced application indicated herein. The invention can prompt a user for a free-form password and can receive a user utterance in response. The utterance can be processed through a speech recognition engine (e.g., during a grammar enrollment operation) to generate an acoustic baseform. Future user utterances can be matched against the acoustic baseform. Results from the future matches can be used to determine whether to grant the user access to a secure resource.

Automatic Morphological Generation for the Indexing of Arabic Speech Recordings

This paper presents a novel Arabic morphological generator (AMG) for Modern Standard Arabic (MSA) which is designed and implemented using Prolog. The AMG is used to generate inflected forms of words used for Arabic audio indexing. These words are also the relevant terms in the Arabic authority system (library information retrieval system) used in this study. The AMG generates inflected Arabic words from the root according to pre-specified morphological features that can be extended as needed. The Arabic word is represented as a feature structure which is handled through unification during the morphological generation process. The inflected forms can then be inserted automatically into a speech recognition grammar which is used to identify these words in an audio sequence or utterance.

Robot‐by‐voice: experiments on commanding an industrial robot using the human voice

PurposeThis paper reports a few results of an ongoing research project that aims to explore ways to command an industrial robot using the human voice. This feature can be interesting with several industrial, laboratory and clean‐room applications, where a close cooperation between robots and humans is desirable.Design/methodology/approachA demonstration is presented using two industrial robots and a personal computer (PC) equipped with a sound board and a headset microphone. The demonstration was coded using the Microsoft Visual Basic and C#.NET 2003 and associated with two simple robot applications: one capable of picking‐and‐placing objects and going to predefined positions, and the other capable of performing a simple linear weld on a work‐piece. The speech recognition grammar is specified using the grammar builder from the Microsoft Speech SDK 5.1. The paper also introduces the concepts of text‐to‐speech translation and voice recognition, and shows how these features can be used with applications built using the Microsoft.NET framework.FindingsTwo simple examples designed to operate with a state‐of‐the‐art industrial robot manipulator are then built to demonstrate the applicability to laboratory and industrial applications. The paper is very detailed in showing implementation aspects enabling the reader to explore immediately from the presented concepts and tools. Namely, the connection between the PC and the robot is explained in detail since it was built using a RPC socket mechanism completely developed from the scratch.Practical implicationsFinally, the paper discusses application to industrial cases where close cooperation between humans and robots is necessary.Originality/valueThe presented code and examples, along with the fairly interesting and reliable results, indicate clearly that the technology is suitable for industrial utilization.

Method and apparatus for creating speech recognition grammars constrained by counter examples

An automated system generates and revises grammars for speech recognizers in a speech recognition system. Given an initial grammar, expressed in terms of non-terminals in Backus-Naur Form (BNF) notation, a sentence generator generates a list of all sentences accepted by the grammar. From this list, a corpus of inappropriate or irrelevant sentences which are accepted by the grammar (counter-examples) is identified. A grammar revisor program uses the original grammar and the list of counter examples, to generate a pruned list from which a revised grammar is generated. The revision process is iterated several times either concatenating or merging pairs of non-terminals until the revised grammar is deemed satisfactory in that it accepts as legal only relevant sentences. The revised grammar is used by the speech recognizer, thus reducing errors in the overall system.