A prosody analyzer enhances the interpretation of natural language utterances. The analyzer is distributed over a client/server architecture, so that the scope of emotion recognition processing tasks can be allocated on a dynamic basis based on processing resources, channel conditions, client loads etc. The partially processed prosodic data can be sent separately or combined with other speech data from the client device and streamed to a server for a real-time response. Training of the prosody analyzer with real world expected responses improves emotion modeling and the real-time identification of potential features such as emphasis, intent, attitude and semantic meaning in the speaker's utterances.

Emotion detection device and method for use in distributed systems

An intelligent query system for processing voiced-based queries is disclosed. This distributed client-server system, typically implemented on an intranet or over the Internet accepts a user's queries at his/her computer, PDA or workstation using a speech input interface. After converting the user's query from speech to text, a 2-step algorithm employing a natural language engine, a database processor and a full-text SQL database is implemented to find a single answer that best matches the user's query. The system, as implemented, accepts environmental variables selected by the user and is scalable to provide answers to a variety and quantity of user-initiated queries.

Intelligent query engine for processing voice based queries

A real-time system incorporating speech recognition and linguistic processing for recognizing a spoken query by a user and distributed between client and server, is disclosed. The system accepts user's queries in the form of speech at the client where minimal processing extracts a sufficient number of acoustic speech vectors representing the utterance. These vectors are sent via a communications channel to the server where additional acoustic vectors are derived. Using Hidden Markov Models (HMMs), and appropriate grammars and dictionaries conditioned by the selections made by the user, the speech representing the user's query is fully decoded into text (or some other suitable form) at the server. This text corresponding to the user's query is then simultaneously sent to a natural language engine and a database processor where optimized SQL statements are constructed for a full-text search from a database for a recordset of several stored questions that best matches the user's query. Further processing in the natural language engine narrows the search to a single stored question. The answer corresponding to this single stored question is next retrieved from the file path and sent to the client in compressed form. At the client, the answer to the user's query is articulated to the user using a text-to-speech engine in his or her native natural language. The system requires no training and can operate in several natural languages.

Distributed realtime speech recognition system

A real-time speech-based learning/training system distributed between client and server, and incorporating speech recognition and linguistic processing for recognizing a spoken question and to provide an answer to the student in a learning or training environment implemented on an intranet or over the Internet, is disclosed. The system accepts the student's question in the form of speech at his or her computer, PDA or workstation where minimal processing extracts a sufficient number of acoustic speech vectors representing the utterance. The system as implemented accepts environmental variables such as course, chapter, section as selected by the user so that the search time, accuracy and response time for the question can be optimized. A minimum set of acoustic vectors extracted at the client are then sent via a communications channel to the server where additional acoustic vectors are derived. Using Hidden Markov Models (HMMs), and appropriate grammars and dictionaries conditioned by the course, chapter and section selections made by the student, the speech representing the user's query is fully decoding to text at the server. This text corresponding to the user's query is then simultaneously sent to a natural language engine and a database processor where an optimized SQL statement is constructed for a full-text search from a SQL database for a recordset of several stored questions that best matches the user's query. Further processing in the natural language engine narrows the search down to a single stored question. The answer that is paired to this single stored question is then retrieved from the file path and sent to the student computer in compressed form. At the student's computer, the answer is articulated using a text-to-speech engine in his or her native natural language. The system requires no training and can operate in several natural languages.

Interactive speech based learning/training system formulating search queries based on natural language parsing of recognized user queries

Sentence based queries from a user are analyzed using a natural language engine to determine appropriate answers from an electronic database. The system and methods are useful for Internet based search engines, as well as distributed speech recognition systems such as a client-server system. The latter are typically implemented on an intranet or over the Internet based on user queries at his/her computer, a PDA, or a workstation using a speech input interface.

System and method for natural language processing of sentence based queries

A process is disclosed for digitizing (more precisely encoding) speech for the purpose of reducing information rate and bandwidth relative to that of prior art means to digitize speech, while enjoying a high signal to noise ratio. Using the the same encoding techniques the process can be used for storage of speech and machine recognition of speech. The process depends on detecting audio waveform zero crossings and generating uniform pulses at the time of the zero crossings. The uniform pulses are created through a regenerative process and are independent of the actual waveform shape save the time of zero crossing. Transmission (or storage) of these uniform pulses permits reconstruction of highly intelligible speech. Ratios of times between zero crossings is used in a new technique for machine word recognition; said ratios allowing recognition regardless of the speakers actual speech rate.

Alden Schloss

Papers

Process for digitizing speech