	US 11,749,286 B2
	ASR training and adaptation
Volodya Grancharov, Solna (SE); Erlendur Karlsson, Uppsala (SE); Sigurdur Sverrisson, Kungsängen (SE); Maxim Teslenko, Sollentuna (SE); Konstantinos Vandikas, Solna (SE); and Aneta Vulgarakis Feljan, Stockholm (SE)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Filed on Dec. 6, 2021, as Appl. No. 17/542,808.
Application 17/217,044 is a division of application No. 16/609,553, granted, now 10,984,801, issued on Apr. 20, 2021, previously published as PCT/SE2017/050457, filed on May 8, 2017.
Application 17/542,808 is a continuation of application No. 17/217,044, filed on Mar. 30, 2021, granted, now 11,610,590.
Prior Publication US 2022/0093107 A1, Mar. 24, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 17/04 (2013.01); G10L 17/06 (2013.01); G10L 17/00 (2013.01)

CPC G10L 17/04 (2013.01) [G10L 17/00 (2013.01); G10L 17/06 (2013.01)]

21 Claims

1. An audio processing method for automatic speech recognition, ASR, said method comprising:

for each audio segment of multiple audio segments in an audio stream comprising audio data of multiple audio programs, each audio segment comprising speech of a single speaker:

obtaining a speaker identifier of a speaker of said audio segment;

determining a program domain identifier based on a media description, wherein the media description could be any information or data element comprising information and metadata of the audio program; and

associating said speaker identifier, said program domain identifier and a speaker domain identifier with said audio segment to enable generation of ASR adaptation parameters based on said speaker identifier, said program domain identifier and said speaker domain identifier,

wherein said speaker domain identifier for said audio segment is based on information or metadata associated with an audio program of said multiple audio programs and said audio segment comprises audio data of said audio program.