Related papers: Halving transcription time: A fast, user-friendly and GDPR-compliant workflow to create AI-assisted transcripts for content analysis

Related papers

Stringalign: Moving beyond summary statistics with a transparent Unicode-aware tool for evaluating automatic transcription models [0.11458853556386794]
This paper presents Stringalign, a Python library designed to simplify the evaluation process for automatic transcription projects.<n>Stringalign's tools to examine and visualise both the rate of errors and the types of errors a model makes, give insights into possible improvements.
arXiv Detail & Related papers (2026-06-14T20:57:47Z)
ATIR: Towards Audio-Text Interleaved Contextual Retrieval [63.68521448682396]
We introduce the Audio-Text Interleaved contextual Retrieval (ATIR) task, where queries can alternate between audio and text modalities.<n>This benchmark substantially addresses the limitations of existing audio retrieval datasets in semantic retrieval.
arXiv Detail & Related papers (2026-04-22T07:11:58Z)
In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions [51.236148875603185]
We extend an existing speech-aware language model to predict timestamps directly alongside transcripts.<n>We introduce a set of novel lightweight training strategies that improve alignment robustness while preserving recognition quality.
arXiv Detail & Related papers (2026-04-14T20:56:24Z)
Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus [0.03262230127283451]
We analyze the implementation of Automatic Speech Recognition into the transcription workflow of the KIParla corpus, a resource of spoken Italian.<n>We show that ASR-assisted transcription can increase transcription speed but do not consistently improve overall accuracy.<n>Despite limitations, ASR-assisted transcription could be integrated into the KIParla transcription workflow to accelerate corpus creation without compromising transcription quality.
arXiv Detail & Related papers (2026-03-17T08:44:37Z)
From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants [0.0]
Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off.<n>This paper presents an end-to-end framework for constructing and evaluating a conversational AI assistant directly from historical call transcripts.
arXiv Detail & Related papers (2026-01-26T07:44:47Z)
PRiSM: Benchmarking Phone Realization in Speech Models [70.82595415252682]
Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis.<n>We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception.
arXiv Detail & Related papers (2026-01-20T15:00:36Z)
Mic Drop or Data Flop? Evaluating the Fitness for Purpose of AI Voice Interviewers for Data Collection within Quantitative & Qualitative Research Contexts [7.938565669618949]
Transformer-based Large Language Models (LLMs) have paved the way for "AI interviewers" that can administer voice-based surveys with respondents in real-time.<n>We evaluate the capabilities of AI interviewers as well as current Interactive Voice Response (IVR) systems across two dimensions.
arXiv Detail & Related papers (2025-09-01T22:44:57Z)
Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration [3.1861081539404137]
This paper explores the application of structured prompt patterns to minimize the number of interactions required for satisfactory AI-assisted code generation.<n>We analyzed seven distinct prompt patterns to evaluate their effectiveness in reducing back-and-forth communication between developers and AI.
arXiv Detail & Related papers (2025-06-02T12:43:08Z)
From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
arXiv Detail & Related papers (2025-05-26T16:08:41Z)
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents [65.36060818857109]
We present a novel framework for extracting and evaluating dialog from historical interactions.<n>Our extraction process consists of two key stages: (1) a retrieval step to select relevant conversations based on key procedural elements, and (2) a structured workflow generation process using a question-answer-based chain-of-thought (QA-CoT) prompting.
arXiv Detail & Related papers (2025-02-24T16:55:15Z)
Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
We show that the pointwise mutual information between a context and a question is an effective gauge for language model performance.<n>We propose two methods that use the pointwise mutual information between a document and a question as a gauge for selecting and constructing prompts that lead to better performance.
arXiv Detail & Related papers (2024-11-12T13:14:09Z)
Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets [1.734165485480267]
We propose a new tool for automatically annotating text using written guidelines without providing training samples. Our results show that the prompt-based approach is comparable with the fine-tuned BERT but without any annotated training data. Our findings emphasize the ongoing paradigm shift in the NLP landscape, i.e., the unification of downstream tasks and elimination of the need for pre-labeled training data.
arXiv Detail & Related papers (2024-06-26T10:44:02Z)
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation [13.800675921118348]
We propose a novel interactive workflow TiCoder for guided intent clarification. We present an empirical evaluation of the effectiveness of the workflow to improve code generation accuracy. We observe an average absolute improvement of 45.97% in the pass@1 code generation accuracy for both datasets and across all LLMs within 5 user interactions.
arXiv Detail & Related papers (2024-04-15T19:16:32Z)
Annotation-free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion [0.0]
We propose a transcription model that does not require any MIDI-audio paired data for pre-training and adversarial domain confusion. In experiments, we evaluate methods under the real-world application scenario where training datasets do not include the MIDI annotation of audio. Our proposed method achieved competitive performance relative to established baseline methods, despite not utilizing any real datasets of paired MIDI-audio.
arXiv Detail & Related papers (2023-12-16T10:07:18Z)
Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation [51.399695200838586]
We propose a streaming Transformer-Transducer (T-T) model able to jointly produce many-to-one and one-to-many transcription and translation using a single decoder. Experiments on it,es,de->en prove the effectiveness of our approach, enabling the generation of one-to-many joint outputs with a single decoder for the first time.
arXiv Detail & Related papers (2023-10-23T11:00:27Z)
Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection [71.20871905457174]
Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text. Previous methods use external knowledge as references for text generation to enhance factuality but often struggle with the knowledge mix-up of irrelevant references. We present DKGen, which divide the text generation process into an iterative process.
arXiv Detail & Related papers (2023-08-30T02:22:40Z)
Transfer of knowledge among instruments in automatic music transcription [2.0305676256390934]
This work shows how to employ easily generated synthesized audio data produced by software synthesizers to train a universal model. It is a good base for further transfer learning to quickly adapt transcription model for other instruments.
arXiv Detail & Related papers (2023-04-30T08:37:41Z)
Just Tell Me: Prompt Engineering in Business Process Management [63.08166397142146]
GPT-3 and other language models (LMs) can effectively address various natural language processing (NLP) tasks. We argue that prompt engineering can help bring the capabilities of LMs to BPM research.
arXiv Detail & Related papers (2023-04-14T14:55:19Z)
Using Document Similarity Methods to create Parallel Datasets for Code Translation [60.36392618065203]
Translating source code from one programming language to another is a critical, time-consuming task. We propose to use document similarity methods to create noisy parallel datasets of code. We show that these models perform comparably to models trained on ground truth for reasonable levels of noise.
arXiv Detail & Related papers (2021-10-11T17:07:58Z)
Experiences with the Introduction of AI-based Tools for Moderation Automation of Voice-based Participatory Media Forums [0.5243067689245634]
We introduce AI tools to filter out blank or noisy audios, use speech recognition to transcribe the voice messages in text, and use natural language processing techniques to extract metadata from the audio transcripts. We present our findings in terms of the time and cost-savings made through the introduction of these tools, and describe the feedback of the moderators towards the acceptability of AI-based automation in their workflow. Our work forms a case-study in the use of AI for automation of several routine tasks, and can be especially relevant for other researchers and practitioners involved with the use of voice-based technologies in developing regions of the
arXiv Detail & Related papers (2021-08-09T17:50:33Z)
Knowledge Distillation for Improved Accuracy in Spoken Question Answering [63.72278693825945]
We devise a training strategy to perform knowledge distillation from spoken documents and written counterparts. Our work makes a step towards distilling knowledge from the language model as a supervision signal. Experiments demonstrate that our approach outperforms several state-of-the-art language models on the Spoken-SQuAD dataset.
arXiv Detail & Related papers (2020-10-21T15:18:01Z)
Exploring Software Naturalness through Neural Language Models [56.1315223210742]
The Software Naturalness hypothesis argues that programming languages can be understood through the same techniques used in natural language processing. We explore this hypothesis through the use of a pre-trained transformer-based language model to perform code analysis tasks.
arXiv Detail & Related papers (2020-06-22T21:56:14Z)
From Natural Language Instructions to Complex Processes: Issues in Chaining Trigger Action Rules [27.61571359186679]
This paper defines a new grammar for complex with chaining machine-executable meaning representations for semantic parsing. An approach to creating datasets is proposed based on this grammar.
arXiv Detail & Related papers (2020-01-08T11:44:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.