At+t Corp.

At&t Intellectual Property I, L.p.

Robert Douglas Sharp

David Bjorn Roe

Pamela Leigh Dragosh

Nambirajan Seshadri

Mazin G Rahim

Richard Vandervoort Cox

Stephen Michael Marcus

A system and method of operating an automatic speech recognition application over an Internet Protocol network is disclosed. The ASR application communicates over a packet network such as an Internet Protocol network or a wireless network. A grammar for recognizing received speech from a user over the IP network is selected from a plurality of grammars according to a user-selected application. A server receives information representing speech over the IP network, performs speech recognition using the selected grammar, and returns information based upon the recognized speech. Sub-grammars may be included within the grammar to recognize speech from sub-portions of a dialog with the user.

System and method of providing generated speech via a network

Recognizing a stream of speech received as speech vectors over a lossy communications link includes constructing for a speech recognizer a series of speech vectors from packets received over a lossy packetized transmission link, wherein some of the packets associated with each speech vector are lost or corrupted during transmission. Each constructed speech vector is multi-dimensional and includes associated features. After waiting for a predetermined time, speech vectors are generated and potentially corrupted features within the speech vector are indicated to the speech recognizer when present. Speech recognition is attempted at the speech recognizer on the speech vectors when corrupted features are present. This recognition may be based only on certain or valid features within each speech vector. Retransmission of a missing or corrupted packet is requested when corrupted values are indicated by the indicating step and when the attempted recognition step fails.

Timing of speech recognition over lossy transmission systems

Recognizing a stream of speech received as speech vectors over a lossy communications link includes constructing for a speech recognizer a series of speech vectors from packets received over a lossy packetized transmission link, wherein some of the packets associated with each speech vector are lost or corrupted during transmission. Each constructed speech vector is multi-dimensional and includes associated features. Potentially corrupted features within the speech vector are indicated to the speech recognizer when present. Speech recognition is attempted at the speech recognizer on the speech vectors when corrupted features are present. This recognition may be based only on certain or valid features within each speech vector. Retransmission of a missing or corrupted packet is requested when corrupted values are indicated by the indicating step and when the attempted recognition step fails.

Speech recognition over lossy networks with rejection threshold

System and method for providing remote automatic speech recognition and text to speech services via a packet network

A system and method of operating an automatic speech recognition service using a client-server architecture is used to make automatic speech recognition (ASR) and text to speech (TTS) services accessible at a client location remote from the location of the main ASR and TTS engines. The present invention utilizes client-server communications over a packet network, such as the Internet or a wireless network, where the ASR/TTS server receives a grammar from the client or selects from a locally second plurality of grammars, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.

System and method for providing remote automatic speech recognition and text-to-speech services via a packet network

Speech recognition over lossy transmission systems

A system and method of operating an automatic speech recognition service using a client-server architecture is used to make automatic speech recognition (ASR) and text to speech (TTS) services accessible at a client location remote from the location of the main ASR and TTS engines. The present invention utilizes client-server communications over a packet network, such as the Internet or a wireless network, where the ASR/TTS server receives a grammar from the client or selects from a locally stored plurality of grammars, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.

A system and method of operating an automatic speech recognition service using a client-server architecture is used to make ASR services accessible at a client location remote from the location of the main ASR engine. The present invention utilizes client-server communications over a packet network, such as the Internet, where the ASR server receives a grammar from the client, receives information representing speech from the client, performs speech recognition, and returns information based upon the recognized speech to the client.

Growing community of inventors

Morristown, NJ, United States of America

Robert Douglas Sharp