# US 8,571,873 B2 · Systems and methods for reconstruction of a smooth speech signal from a stuttered speech signal > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,571,873 B2 - Document ID: US8571873B2 - Status: Granted - Kind: B2 - Application number: 13/088,940 - Filed: 2011-04-18 - Published: 2012-10-18 - Granted: 2013-10-29 - Earliest claimed: 2011-04-18 - Assignees: Nuance Communications, Inc. - Applicants: Om Dadaji Deshmukh; Suraj Satishkumar Sheth; Ashish Verma - Inventors: Om Dadaji Deshmukh; Suraj Satishkumar Sheth; Ashish Verma - Web page: https://patentgrep.com/patent/US8571873B2 ## CPC - G10L 21/0364: for improving intelligibility - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Described herein are methods, systems, apparatuses and products for reconstruction of a smooth speech signal from a stuttered speech signal. One aspect provides for accessing a stored speech signal having stuttering; identifying at least one stuttered region in the stored speech signal; modifying the at least one stuttered region in the stored speech signal; and responsive to modifying the at least one stuttered region, reconstructing a smooth speech signal corresponding to the stored speech signal. Other embodiments are disclosed. ## Claims ### Claim 1 A non-transitory computer storage medium having a computer program product comprising: computer readable program code configured to access a stored speech signal having stuttering; computer readable program code configured to identify at least one stuttered region in the stored speech signal; computer readable program code configured to modify the at least one stuttered region in the stored speech signal, the modifying including at least one of: a) retaining one of a plurality of repeated syllables in the stuttered region in the stored speech signal, b) shortening a steady state of elongated phones in the stuttered region in the stored speech signal; and c) reducing at least one silence/breath region in the stuttered region in the stored speech signal; and computer readable program code configured to, responsive to modifying the at least one stuttered region, reconstruct a smooth speech signal corresponding to the stored speech signal. ### Claim 2 (depends on 1) The computer program product of claim 1, further comprising computer readable program code configured to compare the stored speech signal with the smooth speech signal to detect at least one speaker-specific stutter pattern. ### Claim 3 (depends on 2) The computer program product of claim 2, further comprising computer readable program code configured to provide feedback related to the at least one speaker-specific stutter pattern as a speaker-specific profile. ### Claim 4 (depends on 1) The computer program product of claim 1, further comprising: computer readable program code configured to automatically detect the at least one stuttered region; and computer readable program code configured to automatically label the at least one stuttered region with at least one stutter type. ### Claim 5 (depends on 4) The computer program product of claim 4, wherein to reconstruct a smooth speech signal corresponding to the stored speech signal further comprises applying remedial signal processing based on at least one of location of the at least one stuttered region and a stutter type. ### Claim 6 (depends on 4) The computer program product of claim 4, wherein the at least one stutter type is at least one of syllable repetition, phone elongation and silence/breath. ### Claim 7 (depends on 6) The computer program product of claim 6, further comprising computer readable program code configured to detect syllable repetition via: aligning syllables; and comparing aligned syllables to detect repeated syllables. ### Claim 8 (depends on 7) The computer program product of claim 7, wherein aligning syllables comprises: detecting relative energy minima in the stored speech signal; computing a ratio of energy minima and adjacent maxima in the stored speech signal; and detecting silence between two consecutive energy minima in the stored speech signal. ### Claim 9 (depends on 7) The computer program product of claim 7, wherein comparing aligned syllables further comprises comparing at least two adjacent syllables using frame level features based on distance computation metrics. ### Claim 10 (depends on 7) The computer program product of claim 7, wherein comparing aligned syllables further comprises comparing at least two adjacent syllables using syllable level features capturing dynamic variations over syllable duration in at least one of periodicity, frequency content, and energy. ### Claim 11 (depends on 6) The computer program product of claim 6, further comprising computer readable program code configured to detect phone elongation via detecting at least one of fricatives exceeding a predetermined threshold, voice-bars exceeding a predetermined threshold, and vocalic sounds exceeding a predetermined threshold; wherein elongated phones include phones with or without a formant structure. ### Claim 12 A system comprising: at least one processor; and a memory device operatively connected to the at least one processor; wherein, responsive to execution of program instructions accessible to the at least one processor, the at least one processor is configured to: access a stored speech signal having stuttering; identify at least one stuttered region in the stored speech signal; modify the at least one stuttered region in the stored speech signal, the modifying including at least one of: a) retaining one of a plurality of repeated syllables in the stuttered region in the stored speech signal, b) shortening a steady state of elongate phones in the stuttered region in the stored speech signal, and c) reducing at least one silence/breath region in the stuttered region in the stored speech signal; and responsive to modifying the at least one stuttered region, reconstruct a smooth speech signal corresponding to the stored speech signal. ### Claim 13 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to compare the stored speech signal with the smooth speech signal to detect at least one speaker-specific stutter pattern. ### Claim 14 (depends on 13) The system of claim 13, wherein the at least one processor is further configured to provide feedback related to the at least one speaker-specific stutter pattern as a speaker-specific profile. ### Claim 15 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to automatically detect the at least one stuttered region and automatically label the at least one stuttered region with at least one stutter type. ### Claim 16 (depends on 15) The system of claim 15, wherein reconstructing a smooth speech signal corresponding to the stored speech signal includes applying remedial signal processing based on at least one of location of the at least one stuttered region and a stutter type. ### Claim 17 (depends on 15) The system of claim 15, wherein the at least one stutter type is at least one of syllable repetition, phone elongation and silence/breath. ### Claim 18 (depends on 17) The system of claim 17, wherein the at least one processor is further configured to detect syllable repetition via aligning syllables and comparing the aligned syllables to detect repeated syllables. ### Claim 19 (depends on 18) The system of claim 18, wherein aligning syllables includes: detecting relative energy minima in the stored speech signal; computing a ratio of energy minima and adjacent maxima in the stored speech signal; and detecting silence between two consecutive energy minima in the stored speech signal. ### Claim 20 (depends on 18) The system of claim 18, wherein comparing aligned syllables includes comparing at least two adjacent syllables using frame level features based on distance computation metrics. ### Claim 21 (depends on 18) The system of claim 18, wherein comparing aligned syllables includes comparing at least two adjacent syllables using syllable level features capturing dynamic variations over syllable duration in at least one of periodicity, frequency content, and energy. ### Claim 22 (depends on 17) The system of claim 17, wherein the at least one processor is further configured to detect phone elongation via detecting at least one of: fricatives exceeding a predetermined threshold, voice-bars exceeding a predetermined threshold, and vocalic sounds exceeding a predetermined threshold; wherein elongated phones include phones with or without a formant structure.