Scribd Logo
Upload

Welcome to Scribd!

  • 54 views

    CASSI Speech Recognition

    Uploaded by

    Praveen Lvv
    CASSI is a speech recognition and text-to-speech interface that can be added to embedded devices. It uses continuous, speaker-independent speech recognition and a text-to-phonemes module called Rosetta to synthesize speech. CASSI has a modular design that can run on single or dual processor hardware and integrate speech features through a standardized API. It detects acoustic features from speech input and attempts to match phonemes and words to recognize speech in real time.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd

    CASSI Speech Recognition

    Uploaded by

    Praveen Lvv
    54 views14 pages
    CASSI is a speech recognition and text-to-speech interface that can be added to embedded devices. It uses continuous, speaker-independent speech recognition and a text-to-phonemes module called Rosetta to synthesize speech. CASSI has a modular design that can run on single or dual processor hardware and integrate speech features through a standardized API. It detects acoustic features from speech input and attempts to match phonemes and words to recognize speech in real time.

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    CASSI is a speech recognition and text-to-speech interface that can be added to embedded devices. It uses continuous, speaker-independent speech recognition and a text-to-phonemes module called Rosetta to synthesize speech. CASSI has a modular design that can run on single or dual processor hardware and integrate speech features through a standardized API. It detects acoustic features from speech input and attempts to match phonemes and words to recognize speech in real time.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    54 views14 pages

    CASSI Speech Recognition

    Uploaded by

    Praveen Lvv
    CASSI is a speech recognition and text-to-speech interface that can be added to embedded devices. It uses continuous, speaker-independent speech recognition and a text-to-phonemes module called Rosetta to synthesize speech. CASSI has a modular design that can run on single or dual processor hardware and integrate speech features through a standardized API. It detects acoustic features from speech input and attempts to match phonemes and words to recognize speech in real time.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 14

    CASSI Speech Recognition:

    Adding Speech Recognition to Embedded Devices

    by

    Praveen lvv
    INTRODUCTION

    What is CASSI ?
     Conversay Advanced Symbolic Speech Interface

     It can be used in a variety of embedded systems.


    It runs on either single or dual-processor hardware designs

    Conversay developers and customers write application


    code that uses the CASSI API to integrate speech
    recognition and text-to-speech (TTS) capability into
    embedded products.
    > CASSI provides continuous, speaker-independent
    speech recognition
    What is TTS ?
    Text-To-Speech (TTS):
    CASSI contains two modules for performing TTS:
    Rosetta and a TTS synthesis module.

    Rosetta, the text-to-phonetics unit, accepts


    arbitrary written text as input and outputs a string of
    phonemes for CASSI to synthesize

    process
    of incorporating speech technology
    1. Definition of capabilities
    2. Analysis of hardware resources
    3. User interface design
    4. Development
    HARDWARE ENVIRONMENT:
    Modular nature.

     Suitable for a variety of systems.

     Used with single processor designs where one


    processor handles all component execution.

     Feature extraction and TTS synthesis may be


    separated onto their own DSP (or other front-end signal
    processor)
    Front-End Block:
    The front-end block is used for recognition and TTS functions
    Processor Block (Back-End):

    The processor block performs all other code functions, including


    topic management and search
    AUTOMATIC SPEECH RECOGNISATION

    What does speaker dependent / adaptive / independent mean?


    What does continuous speech and isolated-word mean?

    A continuous speech system operates on speech in


    which words are connected together, i.e. not separated
    by pauses.

    Continuous speech is more difficult to handle because of a variety


    of effects.

    An isolated-word system operates on single words at a


    time - requiring a pause between saying each word.

    This is the simplest form of recognition


    The Process of Speech Recognition
    Acoustic-Phonetic

    Pattern Recognition

    Artificial Intelligence

    INTERFACE
    The Experiment

    ’Yes’ spoken by first person

    ‘Yes’ spoken by the second


    person
    The Basic Steps

     Divide the sound wave into evenly spaced blocks.

     Process each block for important characteristics .

     Attempt to associate each block with a


    Phone, which is the most basic unit of speech,
    producing a string of phones.

    Find the word whose model is the most likely match


    speech recognition systems use the basic three-stage

    Architecture:

    Feature detection in which the


    raw acoustic waveform is
    represented in a more useful
    space

    Probabilistic classification of
    the feature vectors, in which the
    frames are scored as looking
    more or less likely as versions

    Search for best word-


    sequence hypothesis in which
    a word sequence is found that is
    consistent with the constraints of
    lexicon and grammar
    ADVANTAGES OF SPEECH RECOGNISATION

    Easy search and index recorded audio and video data.

    Speech recognition is also useful as a form of input.

     people working in active environment such as hospitals to use computers.

     people with handicaps to use computers.


    CONCLUSION !!!

     Visual cues to help computers decipher speech sounds that


    are obscured by environmental noise.

     Speech-to-speech translation project for spontaneous speech

     Multi-engine Spanish-to-English machine translation system

    Building synthetic voices


    Thank You

    You might also like