Papers by Thomas Schmidt
Querying Interaction Structure: Approaches to Overlap in Spoken Language Corpora (2022.lrec-1)
Copied to clipboard
| Challenge: | In this paper, we address two specific problems arising when indexing and searching interaction corpora with overlapping speaker contributions. |
| Approach: | They propose and experiment with a speaker-based search mode that enables any speaker’s transcription tier to be the basic tokenization layer whereby contributions of other speakers are mapped to this given tier. |
| Outcome: | The proposed method enables any speaker’s transcription tier to be the basic tokenization layer whereby contributions of other speakers are mapped to this given tier. |
Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting ASR-Output (2024.lrec-main)
Copied to clipboard
| Challenge: | Automated speech recognition systems can reduce transcription effort, but few studies have evaluated this potential. |
| Approach: | They compare efforts for manual transcription vs. automatic correction of ASR-output . they use audio recordings from varying settings to create orthographic transcripts . |
| Outcome: | The proposed methods reduce transcription time by 7 times on average for selected data and transcription conventions compared with corrected transcripts . the more complex the primary data, the more time has to be spent on corrections - the paper concludes a similar study could be conducted in 2022 . |
Autoregressive Text Generation Beyond Feedback Loops (D19-1)
Copied to clipboard
| Challenge: | Autoregressive feedback exposes the evolution of the hidden state trajectory to potential biases from well-known train-test discrepancies. |
| Approach: | They combine a latent state space model with a CRF observation model to investigate the state evolution of a hidden state trajectory. |
| Outcome: | The proposed model performs better on unconditional sentence generation compared to baselines while avoiding some prototypical failure modes. |
Improving Sentence Boundary Detection for Spoken Language Transcripts (2020.lrec-1)
Copied to clipboard
| Challenge: | Using data expansion and transfer learning, we find that data expansion does not always improve results. |
| Approach: | They propose to divide spoken language into sentence-like units using Topological Fields model . they also propose to use data from the same domain to test different ML architectures . |
| Outcome: | The proposed model improves the detection of boundary detection in spoken dialogues compared to a sequence tagging approach. |
Using Automatic Speech Recognition in Spoken Corpus Curation (2020.lrec-1)
Copied to clipboard
| Challenge: | Automatic Speech Recognition (ASR) is a new way to make audio-visual data accessible. |
| Approach: | They propose to use automatic speech recognition (ASR) to make audio-visual data accessible by systematic queries. |
| Outcome: | The proposed system has higher recognition scores for the north of Germany vs. lower scores for south of the country. |