Generating Music from Literature

DAVIS, H. W. C.; Mohammad, Saif M.

doi:10.48550/arxiv.1403.2124

Cited by 4 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other work in human-computer interaction has relied upon text analysis tools to build new interactive systems. For example, researchers have automatically generated audio transitions for interviews, cued by signals of mood in the transcripts [34], dynamically generated soundtracks for novels using an emotional lexicon [6], or mapped ambiguous natural language onto its visual meaning [12]. Empath's ability to generate lexical categories on demand potentially enables new interactive systems, cued on nuanced emotional signals like jealousy, or diverse topics that fit the new domain.…”

Section: Applications For Text Analysismentioning

confidence: 99%

Empath

Fast

Chen

Bernstein

2016

Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems

246

View full text Add to dashboard Cite

Figure 1. Empath analyzes text across 200 gold standard topics and emotions (e.g., childishness or violence), and can generate and validate new lexical categories on demand from a user-generated set of seed terms. The Empath web interface highlights category counts for the current document (right). ABSTRACTHuman language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them. We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like "bleed" and "punch" to generate the category violence). Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction. Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the category with a crowd-powered filter. Empath also analyzes text across 200 built-in, pre-validated categories we have generated from common topics in our web dataset, like neglect, government, and social media. We show that Empath's data-driven, human validated categories are highly correlated (r=0.906) with similar categories in LIWC. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.

show abstract

Section: Applications For Text Analysismentioning

confidence: 99%

Empath

Fast

Chen

Bernstein

2016

Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems

246

View full text Add to dashboard Cite

show abstract

“…Categorical models use discrete labels to describe affective responses (Dalgleish and Power 2000) and dimensional ones attempt to model an affective phenomenon as a set of coordinates in a low-dimensional space (Posner, Russell, and Peterson 2005). Text-based emotion recognition systems are usually lexicon-based or machine learned-based, and they are often applied to problems such as sentiment analysis (Pang, Lee, and others 2008), computer assisted creativity (Davis and Mohammad 2014) and text-to-speech generation (Alm 2008). Davis and Mohammad (2014) used a lexicon-based approach to emotion recognition similar to the one we use in this paper.…”

Section: Related Workmentioning

confidence: 99%

“…Text-based emotion recognition systems are usually lexicon-based or machine learned-based, and they are often applied to problems such as sentiment analysis (Pang, Lee, and others 2008), computer assisted creativity (Davis and Mohammad 2014) and text-to-speech generation (Alm 2008). Davis and Mohammad (2014) used a lexicon-based approach to emotion recognition similar to the one we use in this paper. Their approach was used to classify emotions in novels and later generate music for them.…”

Section: Related Workmentioning

confidence: 99%

Bardo: Emotion-Based Music Recommendation for Tabletop Role-Playing Games

Padovani

Ferreira

Lelis

2021

AIIDE

View full text Add to dashboard Cite

In this paper we introduce Bardo, a real-time intelligent system to automatically select the background music for tabletop role-playing games. Bardo uses an off-the-shelf speech recognition system to transform into text what the players say during a game session, and a supervised learning algorithm to classify the text into an emotion. Bardo then selects and plays as background music a song representing the classified emotion. We evaluate Bardo with a Dungeons and Dragons (D&D) campaign available on YouTube. Accuracy experiments show that a simple Naive Bayes classifier is able to obtain good prediction accuracy in our classification task. A user study in which people evaluated edited versions of the D&D videos suggests that Bardo's selections can be better than those used in the original videos of the campaign.

show abstract

“…Also, to the best of the authors' knowledge, MTG is the first AMC system for tabletop games. One of the few works directly related to MTG was proposed by Davis and Mohammad (2014). They used a lexicon-based approach to detect emotions in novels and an AMC technique to compose simple piano pieces that evoke these emotions.…”

Section: Related Workmentioning

confidence: 99%

“…TER is the process of computationally detecting emotions (e.g., anger, sadness and surprise) from text and its systems are usually lexicon-based or machine learnedbased. For example, Strapparava and Mihalcea (2008) used a lexicon-based method similar to Davis and Mohammad (2014) to classify the emotions in newspaper headlines and a Naive Bayes classifier to detect Ekman's emotions in blog posts. NER labels sequences of words in a text which are the names of things, such as characters and location names (Liu et al 2011).…”

Section: Related Workmentioning

confidence: 99%

MTG: Context-Based Music Composition for Tabletop Role-Playing Games

Ferreira

Whitehead

2021

AIIDE

View full text Add to dashboard Cite

This project aims to compose background music in real-time for tabletop role-playing games. To accomplish this goal, we propose a system called MTG that listens to players' speeches in order to recognize the context of the current scene and generate background music to match the scene. A speech recognition system is used to transcribe players' speeches to text and a supervised learning algorithm detects when scene transitions take place. In its current version, a scene transition occurs whenever the emotional state of the narrative changes. Moreover, the background music is not generated, but selected based on its emotion from a library of hand-authored pieces. As future work, we plan to generate the background music considering the current scene context and the probability of scene transition. We also consider to retrieve more information from the narrative to detect scene transitions, such as the scene's location and time of the day as well as actions taken by characters.

show abstract

Generating Music from Literature

Cited by 4 publications

References 0 publications

Empath

Empath

Bardo: Emotion-Based Music Recommendation for Tabletop Role-Playing Games

MTG: Context-Based Music Composition for Tabletop Role-Playing Games

Contact Info

Product

Resources

About