Automated distortion classification
View Patent ↗A method of and system for automated distortion classification. The method includes steps of (a) receiving audio including a user speech signal and at least some distortion associated with the signal; (b) pre-processing the received audio to generate acoustic feature vectors; (c) decoding the generated acoustic feature vectors to produce a plurality of hypotheses for the distortion; and (d) post-processing the plurality of hypotheses to identify at least one distortion hypothesis of the plurality of hypotheses as the received distortion. The system can include one or more distortion models including distortion-related acoustic features representative of various types of distortion and used by a decoder to compare the acoustic feature vectors with the distortion-related acoustic features to produce the plurality of hypotheses for the distortion.
1. A method of automated distortion classification, comprising the steps of:
(a) receiving audio including a user speech signal and at least some distortion associated with the signal;
(b) pre-processing the received audio using a pre-processor to generate acoustic feature vectors;
(c) decoding the generated acoustic feature vectors using at least one distortion model including a plurality of distortion-related acoustic features representative of various types of distortion and used by the decoder to compare the acoustic feature vectors with the distortion-related acoustic features to produce a plurality of hypotheses for a type of the received distortion wherein the various types of distortion include ambient noise, transient noise, and electronics noise;
(d) post-processing the plurality of hypotheses to identify the type of the received distortion; and
(e) using the identified type of the distortion to modify the pre-processor to improve speech signal processing, including at least one of omitting acoustic features that correlate to the distortion type or using a subset of acoustic features available in the pre-processor.
2. The method of claim 1 wherein step (e) includes emphasizing acoustic features that correlate to the user speech signal.
3. The method of claim 1 , wherein steps (a)-(d) are carried out by an automatic speech recognition system installed in a vehicle.
4. A method of automated distortion classification using an automated speech recognition system including an acoustic interface, a pre-processor, a decoder using acoustic models, and a post-processor, the method comprising the steps of:
(a) receiving audio including a user speech signal and at least some distortion associated with the signal;
(b) pre-processing the received audio to generate acoustic feature vectors;
(c) decoding the generated acoustic feature vectors with the decoder using at least one distortion model including a plurality of distortion-related acoustic features representative of various types of distortion and used by the decoder to compare the acoustic feature vectors with the distortion-related acoustic features to produce a plurality of hypotheses for a type of the received distortion wherein the various types of distortion include ambient noise, transient noise, and electronics noise;
(d) post-processing the plurality of hypotheses produced from the decoder to identify the type of the received distortion; and
(e) using the identified type of the distortion to modify the pre-processor to improve speech signal processing, including at least one of omitting acoustic features that correlate to the distortion type or using a subset of acoustic features available in the pre-processor.
5. The method of claim 4 wherein step (e) includes emphasizing acoustic features that correlate to the user speech signal.
6. An automated distortion classification system comprising:
an acoustic interface to receive audio including a user speech signal and at least some distortion associated with the signal;
a pre-processor to pre-process the received audio to generate acoustic feature vectors;
a decoder to decode the generated acoustic feature vectors;
at least one distortion model including a plurality of distortion-related acoustic features representative of various types of distortion and used by the decoder to compare the acoustic feature vectors with the distortion-related acoustic features to produce a plurality of hypotheses for a type of the received distortion wherein the various types of distortion include ambient noise, transient noise, and electronics noise; and
a post-processor to post-process the plurality of hypotheses produced from the decoder to identify the type of the received distortion, wherein the identified type of the distortion is used to modify the pre-processor to improve speech signal processing, including at least one of omitting acoustic features that correlate to the distortion type or using a subset of acoustic features available in the pre-processor.
7. The system of claim 6 wherein acoustic features that correlate to the user speech signal are emphasized.