Interesting links, 17/11/2021

Re-open
Wymysorys
Aragonese

lumaku/ctc-segmentation — Segment an audio file and obtain utterance alignments. (Python package)

Multilingual Transfer of Acoustic Word Embeddings Improves When Training on Languages Related to the Target Zero-Resource Language, pdf

@inproceedings{jacobs21_interspeech,
  author={Christiaan Jacobs and Herman Kamper},
  title={Multilingual {T}ransfer of {A}coustic {W}ord {E}mbeddings {I}mproves when {T}raining on {L}anguages {R}elated to the {T}arget {Z}ero-{R}esource {L}anguage},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1549--1553},
  doi={10.21437/Interspeech.2021-461}
}

Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks, pdf

@inproceedings{kamper21_interspeech,
  author={Herman Kamper and Benjamin van Niekerk},
  title={Towards {U}nsupervised {P}hone and {W}ord {S}egmentation Using {S}elf-{S}upervised {V}ector-{Q}uantized {N}eural {N}etworks},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1539--1543},
  doi={10.21437/Interspeech.2021-50}
}

bshall/VectorQuantizedCPC — Vector-Quantized Contrastive Predictive Coding for Acoustic Unit Discovery and Voice Conversion

worldveil/dejavu — Audio fingerprinting and recognition in Python

Self-Supervised End-to-End ASR for Low Resource L2 Swedish, pdf, data to appear in Kielipankki

@inproceedings{alghezi21_interspeech,
  author={Ragheb Al-Ghezi and Yaroslav Getman and Aku Rouhe and Raili Hildén and Mikko Kurimo},
  title={Self-{S}upervised {E}nd-to-{E}nd {ASR} for {L}ow {R}esource {L2} {S}wedish},
  year=2021,
  booktitle={Proc. Interspeech 2021},
  pages={1429--1433},
  doi={10.21437/Interspeech.2021-1710}
}