Many consumer speech recognition systems are not tuned for people with speech
disabilities, resulting in poor recognition and user experience, especially for
severe speech differences. Recent studies have emphasized interest in
personalized speech models from people with atypical speech patterns. We
propose a query-by-example-based personalized phrase recognition system that is
trained using small amounts of speech, is language agnostic, does not assume a
traditional pronunciation lexicon, and generalizes well across speech
difference severities. On an internal dataset collected from 32 people with
dysarthria, this approach works regardless of severity and shows a 60%
improvement in recall relative to a commercial speech recognition system. On
the public EasyCall dataset of dysarthric speech, our approach improves
accuracy by 30.5%. Performance degrades as the number of phrases increases, but
consistently outperforms ASR systems when trained with 50 unique phrases.

设计了一种基于 qery-by-example 的个人化短语识别系统，针对特殊人群的语音模式进行培训，实验数据表明，该系统相对于商用语音识别系统，无论严重程度都取得了 60% 的识别改进，当训练 50 个独特短语时，一致优于 ASR 系统。

发音障碍者语音的潜在短语匹配

Latent Phrase Matching for Dysarthric Speech

In reverse engineering of database queries, we aim to construct a query from
a given set of answers and non-answers; it can then be used to explore the data
further or as an explanation of the answers and non-answers. We investigate
this query-by-example problem for queries formulated in positive fragments of
linear temporal logic LTL over timestamped data, focusing on the design of
suitable query languages and the combined and data complexity of deciding
whether there exists a query in the given language that separates the given
answers from non-answers. We consider both plain LTL queries and those mediated
by LTL-ontologies.

以正线性时态逻辑 LTL 为例，研究了解决给定答案和非答案的情况下构造查询问题的相关问题，关注于设计合适的查询语言以及决策是否存在特定语言的查询来分离给定答案和非答案的复杂性，同时考虑了纯 LTL 查询和通过 LTL 本体中介的查询。

LTL 本体中介的时间查询的逆向工程

Reverse Engineering of Temporal Queries Mediated by LTL Ontologies

We propose a unified model for three inter-related tasks: 1) to
\textit{separate} individual sound sources from a mixed music audio, 2) to
\textit{transcribe} each sound source to MIDI notes, and 3) to\textit{
synthesize} new pieces based on the timbre of separated sources. The model is
inspired by the fact that when humans listen to music, our minds can not only
separate the sounds of different instruments, but also at the same time
perceive high-level representations such as score and timbre. To mirror such
capability computationally, we designed a pitch-timbre disentanglement module
based on a popular encoder-decoder neural architecture for source separation.
The key inductive biases are vector-quantization for pitch representation and
pitch-transformation invariant for timbre representation. In addition, we
adopted a query-by-example method to achieve \textit{zero-shot} learning, i.e.,
the model is capable of doing source separation, transcription, and synthesis
for \textit{unseen} instruments. The current design focuses on audio mixtures
of two monophonic instruments. Experimental results show that our model
outperforms existing multi-task baselines, and the transcribed score serves as
a powerful auxiliary for separation tasks.

通过一个三合一的统一模型来对音频进行分离、转录和综合，采用一种 pitch-timbre 分离模块来更好地计算音源之间的关系，从而实现零样本学习。

零样本音乐源分离、转录和合成的统一模型

A Unified Model for Zero-shot Music Source Separation, Transcription and  Synthesis

Many tasks in music information retrieval, such as recommendation, and
playlist generation for online radio, fall naturally into the query-by-example
setting, wherein a user queries the system by providing a song, and the system
responds with a list of relevant or similar song recommendations. Such
applications ultimately depend on the notion of similarity between items to
produce high-quality results. Current state-of-the-art systems employ
collaborative filter methods to represent musical items, effectively comparing
items in terms of their constituent users. While collaborative filter
techniques perform well when historical data is available for each item, their
reliance on historical data impedes performance on novel or unpopular items. To
combat this problem, practitioners rely on content-based similarity, which
naturally extends to novel items, but is typically out-performed by
collaborative filter methods.
In this article, we propose a method for optimizing contentbased similarity
by learning from a sample of collaborative filter data. The optimized
content-based similarity metric can then be applied to answer queries on novel
and unpopular items, while still maintaining high recommendation accuracy. The
proposed system yields accurate and efficient representations of audio content,
and experimental results show significant improvements in accuracy over
competing content-based recommendation techniques.

本文提出一种由协同过滤数据样本优化得到的基于内容相似度度量的音乐推荐系统，能够对于新颖或不受欢迎音乐领域的查询给出高精度和高效率的回答，并且在实验中得出了显著的精度改善。