@inproceedings{SchubertSinhaKruegeretal., author = {Schubert, Martha and Sinha, Yamini and Kr{\"u}ger, Julia and Siegert, Ingo}, title = {Speech Recognition Errors in ASR Engines and Their Impact on Linguistic Analysis in Psychotherapies}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7099}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70999}, pages = {203 -- 210}, abstract = {Modern intervention planning in psychotherapies may benefit from predicting process relevant psychotherapy constructs by automated speech analysis. One essential step is the extraction of relevant linguistic speech markers by ASR engines, which because of highly sensible data, work offline. We analyze transcription errors from NeMo, Whisper, and Wav2Vec2.0, focusing on their impact on linguistic markers usually requiring high quality transcripts. By utilizing part-of-speech tagging, we examine error occurrences among different word types. The Linguistic Inquiry and Word Count (LIWC) software aids in extracting markers. We highlight challenges in transcribing spontaneous speech, prevalent in therapy, and compare results with the Mozilla CommonVoice dataset, which features read speech.}, language = {en} } @inproceedings{SinhaHintzSiegert, author = {Sinha, Yamini and Hintz, Jan and Siegert, Ingo}, title = {Evaluation of Audio Deepfakes - Systematic Review}, series = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, booktitle = {Elektronische Sprachsignalverarbeitung 2024, Tagungsband der 35. Konferenz, Regensburg, 6.-8. M{\"a}rz 2024}, editor = {Baumann, Timo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, doi = {10.35096/othr/pub-7096}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-70960}, pages = {181 -- 187}, abstract = {Generative models for audio are commonly used for music composition, sound effects generation for video game development, audio restoration, voice cloning, etc. The ease of generating indistinguishable fake audio with deep learning poses a major threat to personal privacy, online security, and political discourse. Evaluating the quality and realism of these synthetic utterances is crucial for mitigating the potential for misinformation and harm. To assess this threat, this paper conducts a systematic review, using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), on how these deepfake models are currently evaluated. The analysis of 86 papers shows that the majority of the evaluation is conducted on a machine level and highlights a research gap regarding the human perception of deepfakes. This paper explores various methods and perceptual measures employed in assessing audio deepfakes and evaluating their strengths, limitations, and future directions.}, language = {en} }