Speech coding system with a music classifier
AssigneeMindspeed Technologies, Inc.
InventorsAdil Benyassine, Huan-Yu Su
Life of this patent
Estimating the term…
Abstract
The invention provides a speech coding system with a music classifier. An encoder is disposed to receive an input signal and provides a bitstream based upon a speech coding of a portion of the input signal. The encoder provides a classification of the input signal as one of noise, speech, and music. The music classifier analyzes or determines signal properties of the input signal. The music classifier compares the signal properties to thresholds to determine the classification of the input signal.
Claims19
A speech coding system with a music classifier, comprising:
- an encoder disposed to receive an input signal, the encoder to provide a bitstream based upon a speech coding of a portion of the input signal, the speech coding having a bit rate;
- where the encoder provides a classification of the input signal, where the classification comprises at least music;
- and
- where the encoder adjusts the bit rate in response to the classification of the input signal.
A method of classifying music in speech coding system, comprising:
- determining at least one first signal parameter in response to a input signal;
- comparing the at least one first signal parameter to at least one noise threshold;
- when the at least one first signal parameter is not beyond the at least one noise threshold, classifying the input signal as noise;
- when the at least one first signal parameter is beyond the at least one noise threshold, determining at least one second signal parameter in response to the input signal;
- comparing the at least one second signal parameter to at least one music threshold;
- when the at least one second signal parameter is beyond the at least one music threshold, classifying the input signal as speech;
- and
- when the at least one second signal parameter is not beyond the at least one music threshold, classifying the input signal as music.
Dependencies are inferred from the claim text.